🤖 Robotics arXiv Digest

Testing of commercial Advanced Driver Assistance Systems is essential to ensure safety and compliance during type approval and in service operation. However, proving ground scenarios may not reflect real world driving complexity, while geo fencing can require manufacturer collaboration and limit assessment independence. This work presents a methodology for independently testing Assisted Lane Change systems on public roads. A campaign on the A31 French motorway used a test vehicle equipped with a LiDAR based vehicle detection and tracking system. Tests covered combinations of inter vehicle distance and speed between the test vehicle and the take over vehicle. Real time kinematic global navigation satellite system receivers assessed detection and tracking performance. Recorded lane change trajectories were compared with the lane change suppression requirements of UNECE Regulation Number 79. Of 27 predefined lane change manoeuvres, 18 were completed and 9 suppressed. In 6 cases, the system allowed manoeuvres that did not meet regulatory minimum distance requirements. In 3 cases, the deviation remained statistically significant after accounting for measurement uncertainty. To the authors knowledge, this is the first public road campaign designed to assess Assisted Lane Change compliance with Regulation Number 79 safety distance requirements. The results demonstrate the suitability of LiDAR based sensing for this purpose. The methodology can support market surveillance and future regulatory revisions by revealing real world behaviours not covered by approval procedures.

While most phenotyping platforms rely primarily on image-based measurements, advanced plant characterization requires the integration of active physiological sensing modali- ties such as chlorophyll fluorescence. We present an autonomous robotic platform designed to perform targeted fluorescence measurements on plant leaves. The system combines 3D plant reconstruction, geometric analysis, and motion planning to localize suitable measurement points and generate collision-free trajectories for a robotic manipulator. A dense 3D model of the plant is reconstructed from multi-view data and used to extract candidate leaf surfaces based on orientation, accessibility, and sensing constraints. These targets are then integrated into a task-level planning framework that guides the end-effector to precise contact or near-contact configurations required for point-based fluorescence acquisition. The platform enables automated, repeatable, and spatially resolved physiological measurements that go beyond passive imaging. By tightly coupling perception, geometric reasoning, and manipulation, the proposed system provides a robotics-driven approach to high-resolution plant phenotyping and opens new directions for autonomous agricultural inspection and plant-aware manipulation.

Accurate state estimation for autonomous underwater vehicles performing close-range seafloor sampling remains challenging. In low-altitude operation, down-looking cameras over featureless planar seabeds produce scale ambiguity, lateral degeneracy, and inconsistent feature tracking. Meanwhile, inertial-Doppler Velocity Log (DVL) fusion alone provides no mechanism for structural drift correction. We propose a Contact-Aided Factor-Graph Localization framework that treats physical interaction as an informative geometric constraint within a smoothing-based localization formulation. The method tightly fuses suction-based manipulator contact events with adaptive visual odometry, learned object detections, and on-board sensors. Visual odometry relative-pose factors and landmark bearing-range factors are uncertainty-scaled according to inlier statistics to prevent visually weak frames from destabilizing the estimator, while contact events are modeled as high-confidence factors that induce implicit loop closures without appearance-based place recognition. Furthermore, the system can fully initialize online during motion. Experimental evaluation in tanks, harbor, and simulation environments demonstrates that contact-induced constraints significantly reduce trajectory drift and improve object revisit accuracy compared to filtering-based navigation and contact-free graph formulations. These results highlight the role of embodied physical interaction as a localization primitive in perception-degraded underwater environments

Many recent underwater simulators emphasize visual realism at the expense of physical fidelity, focusing on shallow-water effects with limited relevance in deep-water environments and high computational cost. In this work, we shift the focus toward deep-sea physical and sensor realism. We present a physics- and sensor-grounded extension of the Stonefish simulator that augments its hydrodynamic models with stochastic IMU and DVL drift, magnetometer disturbances, higher-order hydrodynamics, terramechanics, pressure-driven environmental variability, and physically based underwater optics. These additions are designed to better capture the forces and measurements shaping the behavior of deep-ocean AUVs, ROVs, landers, ASVs, and gliders, while remaining compatible with real-time simulation. This work advances underwater simulation toward more representative deep-sea operating conditions, which is particularly relevant for long-duration navigation and learning-based autonomy, where inaccurate sensor and environmental models introduce non-physical artifacts and overly optimistic performance. While challenges remain, including complex fluid-structure interactions and full environmental stochasticity, the proposed framework provides a practical foundation for navigation, perception, and autonomy research under deep-sea conditions.

Accurate steering sensing and LiDAR-to-vehicle extrinsics are crucial for reliable path tracking in warehouse mobile robots (WMRs); miscalibration often leads to snaking, weaving, and elevated cross-track error (CTE). In practice, steering ``zero'' is commonly set manually (e.g., eyeballing straightness via a PS4 joystick), while LiDAR extrinsics are assumed from CAD and may drift after maintenance. Such static, manual procedures frequently cause miscalibration in safety-critical environments. This paper presents an Extended Kalman Filter (EKF)--based method for online estimation of steering offset and planar LiDAR extrinsics within a bicycle-kinematics model, providing a principled alternative to manual calibration. Experiments on real datasets show that correcting steering offset reduces CTE substantially, validating the effectiveness of the proposed approach.

Accurate trajectory tracking in cable-driven lower-limb rehabilitation robots is challenging because model uncertainty, external disturbances, joint constraints, and pull-only cable actuation can degrade nominal control performance. Conventional model-based controllers provide an interpretable control structure but remain sensitive to model mismatch, whereas fully learning-based control can reduce transparency and complicate constraint-aware operation. This study proposes a residual deep reinforcement learning-enhanced computed torque control framework in which computed torque control generates the nominal command and a bounded Deep Deterministic Policy Gradient policy supplies only an additional compensating torque. The approach is evaluated in simulation under nominal, uncertain, disturbed, combined, and generalization conditions, together with trajectory-tracking, joint-limit, cable-demand, workspace-feasibility, and cable-Jacobian diagnostics. Across the evaluated conditions, the residual controller improves tracking and disturbance rejection relative to computed torque control while preserving the interpretable model-based command structure and satisfying the reported feasibility checks in the representative evaluation. Broader tests indicate that tracking improvements can persist beyond the representative case while also exposing trajectory-dependent constraint limitations. These results support bounded residual learning as a practical robustness-enhancement strategy for simulation-based rehabilitation robot control and motivate further constraint-aware and experimental validation.

Autonomous driving motion planners generate and select candidate trajectories while accounting for interactions with surrounding agents. However, these evaluations do not certify the actual safety clearance of the selected trajectory. The framework evaluates the trajectory selected by ant planners and calibrates the gap between its plan time margin and realized safety clearance. A differentiable separating axis barrier margin deterministically lower bounds exact signed oriented-bounding-box (OBB) safety clearance, connecting the statistical certificate to safety margin. At plan time, the margin is evaluated using either a nominal prediction and sampled lower tail Conditional Value-at-Risk (CVaR), while post-selection conformal calibration over exchangeable drive sessions absorbs prediction and sampling errors. Conformal calibration provides statistical validity independently of predictor correctness. The method is evaluated on a frozen 300 session nuPlan study using native Predictive Driver Model (PDM) Closed loop proposals. At 10% target miscoverage, sampled lower CVaR reduces the conformal correction from 1.43m to 0.03m and increases the rate of nonnegative safety clearance certificates from 68.7% to 87.3%. Across all evaluated statistics, exact-clearance coverage remains above the 90% target at 93.3--96.7%.

Effective human-robot collaboration in industrial settings requires robots to understand human intentions and assist with task planning, reducing workload. Recent works have explored the use of Multi-modal Large Language Models (MM-LLMs) for task planning in such data-scarce scenarios, leveraging in-context learning to interpret user actions and generate long-horizon action plans in natural language. However, MM-LLMs inherently lack an understanding of system states and do not track state transitions, often leading to hallucinated actions that deviate from the intended goal. Additionally, generating action plans in natural language tends to limit the generated plans to a high level, introducing ambiguity in action execution. To address these limitations, we propose the State-aware Task Estimator and Planner (STEP), which prompts a MM-LLM to explicitly estimate the state of the system and predict the state transitions resulting from executed actions. By forecasting future states alongside actions, STEP ensures task-convergent planning while also providing additional assistance parameters necessary for executing the predicted actions. We evaluate STEP in a simulated environment using a robot assembly task. Our approach outperforms the state-of-the-art by 32.8% in action executability and 14.8% in final-state error.

State-of-the-art action-conditioned video models are typically restricted to a single robot embodiment, preventing them from leveraging the vast corpus of heterogeneous video data that contains rich signals for learning generalizable physics. To bridge this gap, we introduce CLAP, a framework for cross-embodiment action-conditioned video generation capable of being trained on diverse, internet-scale videos across human and robotic agents. CLAP is grounded in the insight that universal physical laws govern spatiotemporal dynamics regardless of the actor. However, cross-embodiment learning is non-trivial because action representations vary sharply across robot platforms and are typically absent in human videos. CLAP addresses this fundamental challenge through the following core contributions. First, CLAP reconciles disparate action spaces using end-effector poses, language instructions, and latent actions. Second, to resolve their individual limitations, CLAP introduces a curriculum-based cross-embodiment learning recipe that first learns foundational physical priors across unlabeled video data using latent actions and subsequently grounds them in end-effector action spaces for zero-shot deployment to real-world tasks. Crucially, CLAP approaches or surpasses state-of-the-art single-embodiment video models in challenging environments like DROID. These performance advantages compound via few-shot adaptation to establish a novel paradigm for training single-embodiment video world models. Ultimately, CLAP delivers the most comprehensive suite of action-conditioned video world models to date - spanning diverse action-conditioning spaces (end-effector, language, and latent) and robot morphologies (including cross-embodiment, DROID, Bridge, bimanual YAM robots, and G1 humanoids). We open-source all code and models. Project Website at https://omni-clap.github.io .

Vision-language-action (VLA) models leverage pretrained vision-language representations for robot control, yet simply adding historical frames does not reliably capture recent physical change. This is especially problematic in multi-stage manipulation, where visually similar states may require different actions depending on prior execution. To address this challenge, we present TemporalFlow-VLA, which learns compact execution history through physically grounded temporal supervision. Using recorded robot states, robot geometry, and calibrated cameras, we construct robot-surface temporal flow as a training-only target and supervise two execution-aligned temporal queries that provide structured history to the action expert. The geometric supervision path is not evaluated at deployment. TemporalFlow-VLA achieves 97.63 +/- 0.26% average success on LIBERO, including 96.60 +/- 0.87% on LIBERO Long, and 85.5%/84.2% Clean/Randomized success across 12 RoboTwin tasks. It shows its clearest advantage over prior methods on longer-horizon, multi-stage manipulation. Controlled history interventions show that action prediction depends on both historical content and temporal order. With asynchronous feature caching, temporal conditioning maintains single-frame-level server-side sampling latency without additional historical-encoding overhead. Overall, TemporalFlow-VLA provides a compact, physically grounded interface for exploiting ordered execution history without explicit motion estimation or geometric processing at deployment.

Recent work shows that pre-trained, instruction-tuned vision-language models (VLMs) perform well at mapping from instructions and observations to high-level plans, but struggle to realize such plans as reliable low-latency action sequences in unfamiliar environments. At the same time, world-model controllers excel at fast observation-to-action control, but lack open-ended task guidance. In this work, we combine these strengths into a single system, Instruct-to-Act, where we train a world-model controller to act autonomously at high frequency when conditioned on sparse, higher-latency, and high-level text instructions generated by a VLM planner. To train controllers to be language-instructable, we relabel segments of controller policy rollouts with synthetic instructions and jointly optimize a behavior-cloning objective along with existing reward-maximizing and world-modeling objectives. We evaluate our proposed approach across seven embodied environments, including three multi-agent environments where VLM planners coordinate through language while trained controllers serve as their actuators. Under matched observation and action spaces, our decoupled approach consistently outperforms controller-only and direct VLM action-generation variants, preserves fast control, and lets us swap in different pretrained VLM planners without fine-tuning, while remaining competitive with strong vision-language-action and multi-agent RL baselines on six of seven tasks.

We introduce Riemann-1.0, a fully causal autoregressive World Action Model for embodied intelligence. Riemann-1.0 jointly models multi-view visual observations, robot states, and embodiment-specific actions within a unified causal autoregressive sequence, representing robot actions and world evolution as causal state transitions. Unlike existing WAMs based on joint generation, video-first prediction, or decoupled modeling paradigms, Riemann-1.0 unifies online robot policy execution and action-conditioned world simulation within a single model, enabling it to function as both an executable robot policy and a multi-embodiment visual world simulator. To scale embodied experience across heterogeneous data sources, we further develop a progressive embodied pretraining framework that unifies learning from egocentric human videos, handheld-gripper demonstrations, and heterogeneous robot trajectories under a shared World Action Modeling objective. Built upon 200K+ hours of interaction data, Riemann-1.0 progressively transfers large-scale embodied experience into executable robot manipulation capabilities. Riemann-1.0 achieves state-of-the-art performance across both simulation benchmarks and real-world manipulation tasks. It achieves success rates of 94.3% on RoboTwin2.0, 99.0% on LIBERO, and 62.6% on the long-horizon compositional benchmark RoboCasa-365, outperforming the previous best method by 8.4% On long-horizon real-world manipulation tasks, Riemann-1.0 achieves a Success Rate (SR) of 85.0% and a Progress Success Rate (PSR) of 94.4%, exceeding the strongest open-source baseline by 15% in SR. These results demonstrate that unified World Action Modeling together with progressive embodied pretraining effectively transforms large-scale embodied experience into generalizable robot manipulation capabilities.

Vision-Language-Action Models~(VLAs) have demonstrated significant promise in generalizing to complex, long-horizon robotic manipulation tasks. However, their performance remains brittle, as they are typically trained on trajectory-monotonic, failure-free demonstrations. This reliance on ``perfect" data leaves them unable to recover from common execution errors, such as a missed grasp, a dropped object, or an unexpected collision. In this paper, we propose FLARE, a novel framework that endows VLAs with robust error recovery capabilities through a ``Retry" and ``Reset" paradigm. First, we introduce a ``Retry" mechanism by injecting perturbation and bridging segments that decouple robot pose from environment state into demonstrations, enabling the policy to autonomously handle execution deviations. Second, to address critical, state-breaking (OOD) failures, we introduce a ``Reset" pipeline. We leverage an MLLM for offline failure analysis to automatically identify OOD states from execution videos. This analysis enables the efficient, targeted collection of a small library of object-centric ``Reset" skills, which are trained to restore the environment to a task-valid state. Our full framework integrates these learned policies. At inference, an online MLLM monitor arbitrates between task execution and ``Reset" skills. Experiments on challenging, contact-rich manipulation tasks show our approach significantly improves task success and robustness.

Robot policies deployed in the wild should have the capability to continually learn new tasks without forgetting existing behaviors. A common approach to combat such catastrophic forgetting is to train on new task data with a replay buffer of previously learned task data. Although this buffer is commonly sampled randomly from all prior experiences, we show that a small set of these experiences contributes greatly in anchoring past performance. We call these experiences Memory Anchors. We identify Memory Anchors in regions where representations of new-task observations collapse onto those of old-task observations even though the tasks require conflicting actions, like when a familiar object must be manipulated in a new way. Rehearsing old data in this region plays a key role in preventing destructive overwriting of past task knowledge, serving as this critical Memory Anchor role. Excluding only 10% Memory Anchors before sampling the buffer leads to more than a 4.5x increase in catastrophic forgetting on the LIBERO benchmark suites. Conversely, enriching the replay buffer with Memory Anchors can decrease high-conflict task forgetting by 63% and enables successful continual learning of two task sequences on a real robot. Videos and additional visualizations can be found at https://robot-adaptation.github.io/MemoryAnchors

This work introduces Configured Failure Trapping, a novel backdoor attack task against Vision-Language-Action (VLA) models, which aims to activate attacks through stealthy textual triggers and induce configured failure modes. Unlike prior backdoor attacks that treat any task failure as a successful attack, Configured Failure Trapping requires the attacker to control how the robot fails (e.g., causing the robot to grasp with a specified positional offset), making it substantially more challenging and hard to detect. To support the new task, we propose an effective data engine for synthesizing high-quality target trajectories and an automated suite for measuring configured-failure fidelity. Then, based on this foundation, we construct two new benchmarks, namely Trap-LIBERO and Trap-RoboTwin, that instantiate Configured Failure Trapping across four representative failure modes. To address this task, we identify sparse action deviation as a critical challenge and accordingly propose a novel method named TrapVLA, which explicitly learns trigger-induced action residuals to steer the policy toward the configured failure behavior. Extensive experiments across simulation benchmarks and real-world robotic settings show that TrapVLA effectively injects configured failure modes into VLA models while largely preserving performance on clean data. Project page: https://john-liua.github.io/TrapVLA/

Contrastive reinforcement learning (CRL) scales effectively in goal-conditioned tasks by casting policy learning into a self-supervised contrastive objective. However, in a failure-terminated Markov decision process, established CRL considers pre-failure future goals only when constructing positive samples, without accounting for the probability mass removed by failure termination. Our theoretical analysis shows that this omission induces a systematic overestimation bias in goal-reaching values. Consequently, near-failure trajectories provide disproportionately strong supervision of success despite retaining little future occupancy. Unsafe actions can thereby be reinforced through catastrophic failure bootstrapping, leading to failed policy learning and unsustainable goal-reaching behaviours. To address this problem, we introduce two minimal yet strong corrections: mass-weighted InfoNCE corrects the overweighting of short surviving futures in critic learning, and a log-survival-mass score restores the missing survival mass in policy optimization. The resulting method, Safe Contrastive Reinforcement Learning (Safe-CRL), requires only the one-bit signal provided by failure termination to scale safe goal-conditioned policy learning. Across twelve failure-prone robot navigation and locomotion tasks, Safe-CRL consistently improves survival and substantially outperforms the Scaling-CRL baseline in goal-reaching performance. Additionally, deep Safe-CRL policies exhibit complex failure-avoidance behaviours. This study completes the CRL theory under failure termination and provides a scalable safe RL framework. The code is available via https://github.com/RomainLITUD/safe-crl.

Pretrained vision-language-action (VLA) policies provide strong priors for robot manipulation, yet adapting them online to fine-grained biomedical tasks remains challenging. Task success often hinges on subtle, view-dependent visual cues, while task-level rewards provide little guidance about which regions matter, making it difficult to learn task-relevant visual grounding from limited real-robot interaction. Online adaptation is further constrained by the computational cost of VLA inference and replay-based updates. We introduce GRAFT (Grounded Reinforcement Adaptation for Fast Task Learning), a framework for efficient online VLA adaptation through grounded perception. GRAFT uses region-level supervision to learn view-specific visual anchors that focus perception on task-relevant local cues without requiring region proposals at deployment. It further combines single-step action generation with cached visual-language prefix reuse to accelerate online learning. Across four biomedical manipulation tasks, GRAFT improves success rates by 25 percentage points under matched adaptation budgets, while reducing the computational overhead of online policy updates.

We study the problem of decentralized, self-organized task sharing for a swarm of heterogeneous robots that collaborate in transportation or other objectives that require coordinated motion planning. To this end, we present theoretical and practical results for the simple but effective mechanism of \emph{bucket brigades} for load balancing, in which a team of heterogenous robots share a spatial task in a confined, one-dimensional space, while only being able to sense collisions with neighbors or walls. The goal is to optimize throughput of the overall system, without central control or information, aiming at an interval partition proportional to robot velocities. We address possible chaotic system behavior by developing a stabilization mechanism based on simple local aid, a ``token'', that temporarily decelerates robots after an encounter. This purely local change eliminates persistent oscillations, resulting in convergence towards a stable system state. We accelerate system convergence by comparing a single boundary token to ubiquitous two-directional tokens and optimizing the deceleration factor. Event-driven simulations report convergence times and robustness: For a large variety of perturbations (such as robot deletion, position or velocity jittering), the system reliably re-converges. The results suggest a local, practical mechanism for robust load balancing for heterogeneous teams of robots that promises an effective tool as basis for more complex scenarios.

The marine science community increasingly relies on Marine Autonomous Vehicles (MAVs) to collect the critical environmental data required to understand global ocean systems. However, as these operations scale, manually routing and planning large autonomous fleets becomes exponentially complex and time-consuming. To address this, we propose a mixed-integer linear programming (MILP) model designed to automate and optimise MAV deployment schedules. The model accounts for strict operational constraints, including battery capacities and time windows for data collection, while aiming to maximise total data collection and minimise both the number of deployed vehicles and their energy consumption. A key novelty of this framework is integrating conventional ship itineraries, allowing MAVs to support vessels with mid-mission battery swapping or accelerated transit between waypoints. Computational experiments demonstrate that the model is highly scalable, solving routing problems for fleets of dozens of MAVs in seconds, and scaling to hundreds of vehicles in only a few minutes. Beyond operational scheduling, the framework serves as a robust simulation tool for evaluating 'what-if' scenarios and analysing the impact of varying parameters on deployment strategies. Finally, the solution generates a suite of visualisations designed to enhance explainability and support strategic decision-making for stakeholders.

Space-efficient warehouse layouts often contain single-agent-width aisles and dead-end workstations where robots have few places to wait without blocking others. In Multi-Agent Pickup and Delivery (MAPD) on such constrained layouts, robots must accept online pickup-delivery tasks while preserving protected waiting locations called Havens. The Safe HAven Retreat Planner (SHARP) introduced a mechanism that extends each committed task path with a validated retreat to the agent's dedicated initial Haven, but fixed-Haven commitments can send agents toward distant Havens after deliveries. We present A-sharp (Adaptive SHARP), which changes an agent's retreat target at task assignment time. A naive switch can cause two agents to rely on the same waiting location or let another committed path pass through a location that is still occupied or reserved. A-sharp prevents these failures with an availability test for candidate Havens and a pending-release rule that keeps the previous Haven protected until the agent departs. Under explicit Haven-structure and Safe Interval Path Planning (SIPP) assumptions, we prove invariant preservation and finite-release completeness: every task in any finite release sequence is delivered in finite time. Across 72,000 runs on 14,400 paired map-agent-count-rate-seed cases over four maps, both SHARP and A-sharp complete their respective 14,400 runs. For makespan (final delivery time), a prespecified paired comparison with Holm correction over all 138 configurations with more Havens than agents finds A-sharp significantly better in 107 configurations and never significantly worse than SHARP; on the tested tree map, the median reduction is 16.7%.

Operational requirements developed with the City of Braunschweig frame municipal micromobility planning under geofenced exclusions, mandatory retained sites, spacing rules, and area-level caps. Each policy edit requires a new feasible plan; full-set greedy takes tens of seconds per alternative at city scale. We present CLIPPER (Constraint-exact Low-latency Iterative Planning with Pooled Evaluation and Replay). It forms bounded candidate pools but recomputes exact current gains and checks every active constraint before selection. Coverage from each candidate alone sets the initial order. Offline full-set scans measure gains omitted by the pool; online, a conservative bound triggers expansion or audit. CLIPPER-F gives each proposal group the same number of candidate slots. Across Braunschweig, Munich, and Berlin, its mean coverage over complete chains stays within 0.245 percentage points of full-set greedy under the same policy, with 13.6--28.9 times lower mean rollout time. CLIPPER-A instead distributes one shared candidate budget across the groups. Under its coverage-prioritized policy, it uses 9--15% of full-set greedy's rollout time under the same policy, with mean gaps of 1.82 percentage points in Braunschweig, 0.12 in Munich, and 0.27 in Berlin. Together, CLIPPER enables rapid, replayable comparison of recorded city-scale planning states while enforcing every encoded model constraint.

Explorable image-to-scene generation is essential for applications in gaming, robotics, and virtual reality. Existing methods based on video diffusion model (VDM) commonly rely on incomplete conditioning signals such as sparse point clouds or 2D panoramas, leading to stochastic hallucinations, long-term drifts and suboptimal 3D consistency. We present SpatialCrafter, a novel two-stage framework that addresses these issues by introducing a global 3D proxy for high-fidelity image-to-scene generation. Specifically, we decompose the generation process into global proxy generation and appearance refinement. For proxy generation, we propose a Point-anchored Sparse Structure~(PaSS) Flow module that predicts a spatially aligned and geometrically consistent 3D proxy. For appearance refinement, we re-frame the VDM as a Generative Deferred Refiner which synthesizes high-frequency photorealistic details upon proxy-defined scene geometry. To better integrate the proxy with the pre-trained VDM, we introduce Parallel Geometry Injection and Proxy-Aware Corruption training strategies, which improve robustness to proxy artifacts without disrupting the pretrained generative manifold. Furthermore, as no suitable dataset exists for this explorable scene generation task, we construct a new large-scale dataset of 115K scenes. To the best of our knowledge, it is the first hybrid dataset for image-to-scene generation. Extensive experiments on both synthetic and real-world datasets show that SpatialCrafter outperforms state-of-the-art methods, mitigates long-term drift, and remains robust and consistent under rapid camera motion and extreme viewpoint changes. Code, models, and the newly constructed dataset will be publicly released. See more at https://fangchuan.github.io/SpatialCrafter/.

Recent advances in SLAM have leveraged 3DGS for photorealistic reconstruction and novel view synthesis. However, most methods rely on RGB-D input, which is unavailable on consumer-grade smartphones, and few integrate 3DGS within a collaborative framework. Therefore, we present CGS-SLAM, a hybrid decentralized/centralized system enabling multi-agent 3DGS SLAM using only RGB and inertial data. Each agent performs local tracking with inertial data as a motion prior and reconstructs a scaled map using a metric monocular depth estimator (Depth Pro). Keyframe encodings are shared among agents, enabling dynamic keyframing in regions of spatial overlaps with other agents, enhancing submap alignment. Afterwards, a central server aligns submaps using VGGT as a view alignment model. This bidirectional communication keeps communication cost low during mapping and global reconstruction in difficult GNSS-denied environments. Experiments on multiple datasets demonstrate competitive tracking performance, improved rendering quality over state-of-the-art methods, and accurate submap alignment.

This paper introduces Embodied Scene Rearrangement Planning (ESRP), a novel task requiring embodied agents to rearrange furniture in 3D scenes to match a target configuration using only egocentric observations and a top-down target layout. Unlike prior rearrangement tasks, ESRP precludes global state access and introduces mutual object occlusions, reflecting the practical constraints of real-world robotic deployment. These factors make aligning partial egocentric observations with the global target layout particularly challenging for long-horizon planning. To facilitate research, we present ESRP-Bench, a comprehensive benchmark built on OmniGibson featuring over 5,400 scene pairs and 8,200 objects. We define three multi-level metrics to evaluate rearrangement quality and provide four baselines: a hierarchical task-and-motion planning method, a vision-language-model-based method, and two learning-based approaches (IL and RL). Experimental results demonstrate that current methods struggle to complete the task efficiently, highlighting ESRP as a challenging frontier for embodied agents in scene understanding and long-horizon task planning. This work serves as a stepping stone toward deploying intelligent agents in real-world scenarios. Project page: https://pie-lab.cn/ESRP/.

Embodied agents need environments that are visually diverse, physically interactive, and changing over time. Procedural simulators can generate large interactive scene collections, and recent 4D generators produce compelling visual dynamics. Combining these properties in one environment, however, still demands extensive manual effort, and the result is rarely editable or controllable enough to reuse at scale. We present 4DSynth, a controllable procedural system that turns a natural-language description, a blueprint mask, or a single photograph into an editable 4D environment with explicit geometry, animated actors, collision-free trajectories, and physics-ready simulation state. Multiple scene routes share one geometry-grounded representation, so the same pipeline handles animation, camera planning, rendering, and task generation. To validate the full pipeline, we construct 4DSynth-Nav, an interactive navigation benchmark generated entirely from 4DSynth's procedural scenes. Two vision-language models evaluated across three difficulty tiers both fail the majority of tasks and stall after early subtasks. The same procedural controllability that produces these environments also makes each failure reproducible and each difficulty axis independently tunable. This paper presents both a controllable generation pipeline and the scalable benchmark it enables, offering a practical foundation for developing and evaluating embodied agents.

Robots that can change their morphologies and behaviors for different tasks and environments hold great promise for adaptable, multifunctional systems. Modular reconfigurable robots (MRRs) can achieve such functionalities by docking and rearranging individual units, but most rely on rigid modules that lack structural compliance, resulting in limited capabilities. Continuum robots offer compliance through flexible backbones, yet they cannot self-reconfigure into task-adaptive multi-robot configurations. Here, we introduce an MRR that unifies the advantages of both architectures by combining a tensegrity-based compliant body with claw-based connection mechanisms. Each robot can manipulate and locomote independently, and multiple robots can self-reconfigure into different morphologies (e.g., chains, loops, branches) for cooperative manipulation and locomotion. We demonstrate the robots' capability across diverse tasks and environments, including coordinated object manipulation and transport, multimodal locomotion, and loco-manipulation in real-world scenarios. These results lay a foundation for adaptable and multifunctional robotic collectives, with broad potential applications in manufacturing, space exploration, and search-and-rescue operations.

Stable support remains challenging in robotic disassembly of irregularly shaped products. As components are progressively removed, the available support surfaces, mass distribution, and task loads change throughout the process. A fixture layout designed for one workpiece state may therefore become infeasible at later stages, motivating unified support planning over the complete disassembly sequence. This paper presents a modular vacuum-based fixturing system that plans one shared support configuration for the complete disassembly sequence of a screwdriver or shaver, allowing each sequence to proceed without fixture reconfiguration. To search the mixed continuous--discrete layout space under repeated cross-stage evaluation, a denoising diffusion probabilistic model generates physics-informed initial configurations that are refined through Bayesian optimization. Robotic screw and component-removal experiments verified the disassembly feasibility of the planned layouts, while 11 directional-load tests quantified their stability. Comparisons between the measured operational loads and directional responses yielded mean empirical stability margins of 66.9% for the screwdriver and 81.6% for the shaver. These results demonstrate that a product-specific shared layout can provide stable support throughout the tested robotic disassembly sequence.

Robotic grippers face substantial challenges in grasping and manipulating thin objects. Most existing grippers rely on highly precise approach and grasp motions, which limits robustness and reduces applicability. This paper explores thin-object grasping using books as a representative example. Here, we propose a novel solution that integrates an active surface with underactuated compliance to achieve stable grasping of thin objects without complex control. First, an underactuated gripper with an active surface is designed. The active-surface thumb performs in-hand repositioning of the target book without requiring adjustments of the robot arm or the other fingers, while the underactuated fingers establish compliant contact conditions with the environment, and the reconfigurable structure enables reliable grasping of books under different configurations. Second, we establish a kinematic model of the gripper, and determine the initial grasp postures for two representative scenarios (books lying flat on a desktop and books vertically packed in a shelf). Third, by analyzing the physical model of a book lying on a table and its interaction with the gripper and the environment, we systematically optimize the structural parameters and grasping strategy. Finally, extensive experiments validate the effectiveness of the proposed gripper and strategy. The results demonstrate strong robustness and adaptability when grasping thin objects placed flat (including books, paper, fabric, plastic film, and mouse pad), as well as a high success rate when grasping vertically packed books. Moreover, the proposed gripper can reliably complete long sequential "grasp-place" tasks.

We present an online learning framework that enables a bimanual robot to acquire diverse juggling patterns directly on physical hardware within minutes, even with a significant sim2real gap. One of the most important lessons from this work is that a model, even when far from reality, can be extremely useful for learning. This motivates a central philosophy of our approach: learning should build upon the robot's current knowledge rather than replace it. Our regularized memory-based learning puts this principle into practice by learning a local model from accumulated experience while retaining the global prior model to extrapolate where experience is sparse. This enables efficient and stable online learning from each new experience without resorting to uninformed exploration over a vast space of possible behaviors. Equally important to continual on-robot learning is safety, allowing the robot to repeatedly practice and improve in the real world. We construct a mutually reachable set that allows safe transitions between successive throws and catches, without driving either arm into a state from which its next action would require violating the robot's joint or actuator limits. Together, these ideas enable a bimanual robot with multi-fingered hands and onboard vision to safely learn and compose five canonical three-ball juggling patterns, including cascade, tennis, half-shower, shower, and box, within less than 5 minutes of real-world interaction. More broadly, this work points toward robots that build upon imperfect prior knowledge and continually refine their behavior through their own real-world experience.

Humans traverse complex terrain over long distances without losing balance, whereas perceptive humanoid policies become fragile as perception and control errors accumulate. We present SOLO, a unified framework addressing two compounding causes of this long-horizon fragility: dense terrain reconstruction smooths action-critical details, and pointwise imitation lacks temporal credit assignment. Its Query Reconstructor (QR) uses Fourier-encoded cell queries to retrieve spatially specific evidence from depth-proprioception tokens, preserving sharp terrain boundaries. Trajectory-Aware MSE (TA-MSE) Distillation adds next-state teacher-student disagreement to the PPO reward, enabling Generalized Advantage Estimation to propagate future disagreement penalties to preceding actions. In simulation, QR reduces height-map L1 error by factors of 3.3-4.0, while TA-MSE surpasses PPO and MSE+PPO in curriculum progression. On stress-test terrains, SOLO achieves 97.5% mean traversal success and 96% stepping-stone success, versus 75.0-75.6% and 0-3% for dense-reconstructor variants. Deployed zero-shot with only a chest-mounted depth camera and proprioception, SOLO completes a continuous 1.5-km outdoor route and an indoor mixed-terrain course. Project page: https://sunpihai-up.github.io/solo/