When a robot practices without human resets, every attempt still costs wall-clock time, actuator wear, and sometimes a person's attention, yet the schedulers that decide what to practice next treat attempts as free. We present an open, low-cost testbed for measuring these costs: a self-built SO-101 arm runs two demonstration-trained ACT policies that reset each other, with a vision-based success detector and a ledger that records the time, joint travel, and human interventions of every attempt. We formulate cost-aware practice scheduling, in which task selection is rewarded by measured competence gain net of embodied cost, and specify in advance the comparison that will test it. Its first two conditions, run on hardware for 51 minutes of robot time, show that a fixed retry limit did not reduce the share of execution time lost to failures (36%, against 27% for a feasibility rule; not significant) and saved no robot time. The logs suggest why: failures showed no sign of clustering, so a retry right after a failure was as likely to succeed as any other attempt. The ledger also shows that most of the retry rule's extra human time came from cubes knocked out of reach rather than from the rule itself, and a cost-aware rule replayed on the logs recovers the sensible choice without a hand-set limit. We also report lessons from building the system, including a coverage effect in which concentrating demonstrations in a smaller workspace raised success there from 8/20 to 10/10.
https://arxiv.org/abs/2611.19979
Robots that travel long distances through public outdoor spaces must do more than avoid obstacles: they must remain on terrain suited to their mobility and decide when to proceed, yield, or detour around pedestrians, cyclists, vehicles, traffic signals, and temporary restrictions. These decisions are difficult because their correctness often depends on how a scene evolves, such as whether an approaching car is slowing or a cyclist will cross the robot's path. Vision-language models (VLMs) can interpret such cues, but they reason over images that lack metric geometry and motion. Supplying this evidence at every step is too slow for real-time navigation, and hand-crafted triggers cannot anticipate the open-ended variety of outdoor situations. We present MOSU2, a long-range navigation system with two-stage trajectory selection, in which first-stage contextual reasoning determines when additional evidence is needed and what to retrieve. Only when an interaction remains unresolved does the first stage trigger the second stage to retrieve geometric and dynamic information and align it with scene context to make navigation decisions. Building on MOSU, MOSU2 follows routes from GPS-based route planning and filters candidate trajectories through multi-modal traversability analysis before selecting a trajectory to move the robot. In real-world experiments spanning stop gestures, construction sites, crosswalks, and roads shared with vehicles, cyclists, and pedestrians, MOSU2 raises mean navigation success from 61.8% to 94.2% and condition-detection accuracy from 72.2% to 91.4% over its single-image predecessor, at about 2.2 times its mean decision latency. Project website: this https URL
https://arxiv.org/abs/2611.11148
Autonomous vehicle (AV) decisions at intersections affect the delay, braking, and motion smoothness of surrounding human-driven vehicles (HDVs). Learning socially compatible behavior requires connecting imagined interaction outcomes with feedback from executed actions. We propose a world-model reinforcement learning framework combines imagined policy improvement with direct value and policy calibration from finalized interactions, balancing AV progress with HDV interaction burden. An interaction-aware latent model supports imagination, while off-policy correction and replay updates enable observed rewards and transitions to supervise both the critic and actor. Simulation experiments at an unsignalized intersection achieve a 100% success and reductions in following-HDV acceleration variation of 65.5% and 44.0% relative to PIWM and DreamerV3, respectively. Ablations identify complementary roles for value calibration in reducing HDV burden and policy calibration in improving passage efficiency. Tests under out-of-distribution traffic shifts further show lower ego jerk and HDV acceleration variation than PIWM at comparable passage times.
https://arxiv.org/abs/2611.19969
A robot may know how to move an object yet still need to learn where it belongs. When a person rejects a placement, the robot must decide whether the correction applies only to that situation or expresses a broader rule. We study this problem in CRAFT (Contextual Requirement Adaptation with Frozen Tools), a framework for learning local requirements without retraining robot skills. It records physical success separately from whether an action meets the requirement. Our scope ladder uses memory when an action has already been judged in a nearly identical situation. Elsewhere, it combines memory, explicit rules and a learner for requirements beyond those rules, weighting their predictions by how well they predicted earlier feedback. Controlled studies show gains over correction memory alone in utility, which rewards acceptable actions and charges for mistakes and questions. In camera-grounded robot simulations, the ladder asks fewer questions than language-model agents with persistent memory, but some of those agents take fewer wrong actions and succeed more often after requirements change. All execution failures and timeouts remain in the evaluation. These results support combining specific memories with broader rules, while leaving reliable adaptation to changing requirements unresolved. All evidence comes from simulation with generated requirements and simulated feedback.
https://arxiv.org/abs/2611.19952
As older adults increasingly live alone, emergency support becomes an important function for home companion robots. In Australia, demand for the care and support workforce is projected to nearly double between 2020-21 and 2049-50. Service robots such as robot dogs may support older adults by combining everyday companionship with assistance when human support is not immediately available. We present the design and implementation of a domestic companion-robot system on a Unitree Go1 quadruped platform that combines companionship with emergency awareness and response. The system uses a three-stage interaction model consisting of companion, danger-awareness, and emergency modes. A rule-based escalation policy combines signs detected from visual and speech input to determine the current risk level and adjust how long the robot waits for the user to confirm safety before entering emergency mode. Additional detected signs can shorten this waiting time. Users can confirm safety, request immediate help, stop robot motion, or reset the system. We verified the implemented decision rules and escalation timing through 105 automated trials and 25 staged physical trials. Additional visual evidence shortened the waiting time, and the system entered emergency mode when the waiting time ended without confirmation.
https://arxiv.org/abs/2611.19932
We present Lao Siji, an end-to-end driving policy that ranks third in the 2026 NVIDIA AlpaSim E2E Driving Challenge, ahead of most entries built on foundation models. Instead of training from scratch on a general-purpose vision backbone, we adapt openpilot, an open-source L2 production model. We freeze its vision encoder and fine-tune the policy layers with an ego-state adapter and a route memory. On closed-loop rollouts in neural-reconstructed scenes, we supervise the policy with a privileged map teacher for lateral self-correction and a body-extent loss for road and obstacle clearance, while distilling the base model's remaining outputs to retain car following. Ablations show that self-correction samples carry the gain, while the clearance loss substitutes for them where no teacher exists. Longitudinal safety instead rests on the base model's lead-vehicle estimate behind a rule-based speed layer. Longer training, imitating human logs, and human-log speed targets yield either no measurable gain or adverse effects. Without further training, Lao Siji also places among the leaders on HUGSIM and Odyssey. The final training takes only one GPU-hour and shifts the weights by 3.9% from the shipped model. Code will be released after review.
https://arxiv.org/abs/2611.19922
Agentic navigation must maintain goals and adapt actions from incomplete evidence despite execution failures and delayed inference. We present AgenticJevNav, which links goal-directed planning, evidence memory, event-triggered verification, and bounded execution. The Agent plans from RGB, odometry, memory, and feedback, retaining goal ownership while authorizing a bounded action set. Jev reviews structured evidence after blocked/failed execution or two consecutive low-progress segments. Version, freshness, and once-only checks govern decision application. A single executor and independent RGB reflex constrain motion. Goal revisions revoke obsolete requests and actions before replanning. Across six simulated task families, AgenticJevNav achieves 73.33% SR over 60 trials, 21.67 percentage points above the next-best Agent-only aggregate control under differing historical protocols. A real-world GENISOM L1 quadruped deployment achieves 70.0% success over 30 trials, including bounded search reporting. Together, the simulation and physical-robot results demonstrate the effectiveness of the proposed architecture, while remaining failures highlight opportunities to improve grounding, approach planning, and runtime.
https://arxiv.org/abs/2611.19912
The protective separation zone of a collaborative robot cell is commonly dimensioned for a worst case that disregards where the operator is actually present during the task. This paper presents a camera-based, data-driven method that configures this zone from observed operator occupancy. Operator positions accumulated over several production shifts are aggregated into an occupancy heatmap, from which a protective field is derived that trades off the achievable robot velocity against the required safety distance, following the speed and separation monitoring principle of ISO/TS 15066. The resulting configuration is advisory, that is, reviewed within the risk assessment rather than applied autonomously to the robot controller. The method, which builds on a pose-based perception pipeline with activity recognition, was evaluated in two operational cells at two industrial partners, where the protective field could be reduced by approximately 17% and a productivity increase of 9% was measured. However, adoption proved to depend on more than the demonstrated gain alone.
https://arxiv.org/abs/2611.07621
World Action Models (WAMs) have emerged as an important paradigm in robot learning, jointly predicting future scene states and robot actions from current observations and instructions. However, future states entangle task-related changes with large amounts of task-irrelevant content, such as static backgrounds, which weakens the model's ability to capture changes relevant to task execution. To address this, we propose Difference World Action Model (DiffWAM), a Mixture-of-Experts (MoE) framework that enhances world representations by jointly learning future-state prediction and consecutive visual difference prediction. We define consecutive visual differences as differences between the latent representations of consecutive observations, providing an explicit learning signal for temporal variation. The framework comprises a World Expert for future frame prediction, an Action Expert for action generation, and a Diff Expert for predicting these latent differences along the trajectory. A structured unidirectional attention mask conditions the Diff, World, and Action Experts solely on the current-frame representation while blocking attention between experts. This design allows both the World and Diff Experts to be removed during inference, introducing no additional inference overhead. DiffWAM achieves state-of-the-art performance on the LIBERO and RoboTwin 2.0 benchmarks and substantially improves over FastWAM on real-world manipulation tasks. Specifically, it attains average success rates of 98.8%, 92.65%, and 88.3%, outperforming the state-of-the-art baseline (i.e., FastWAM) by 1.75, 1.55, and 15.0 percentage points, respectively.
https://arxiv.org/abs/2611.19904
Most robot navigation stacks implicitly bind mapping, localization, planning, and control to specific representations and data flows, yielding architectures hard to extend, compare experimentally, or reason about end-to-end timing. This is critical in heterogeneous scenarios, where multiple spatial representations, sensing modalities, and coordinate frames coexist and evolve at different rates. This paper presents a navigation architecture centered on an explicit, shared navigation state that serves as the sole interaction interface between modular components. Constraining mapping, localization, planning, and control to operate over this shared state enables interchangeable, representation-agnostic pipelines under explicit compatibility and timing contracts. We realize this architecture as EasyNav, an open source ROS 2 framework, and validate it through real-robot experiments, including indoor navigation with laser sensing and large-scale indoor-outdoor navigation with GPS and 3D LiDAR across multi-level routes. Compared with Nav2 under matched conditions, EasyNav reduces reaction latency from 377 to 33 ms indoors and from 71 to 8 ms outdoors, while also using less CPU and memory.
https://arxiv.org/abs/2611.19894
Video world models promise to predict the future of a scene from its present. Do current models keep this promise? We probe this question counterfactually. When a small change to the present flips the future, such as a box resting a few millimeters before or past a table edge, a model that tracks the state of the world must flip its prediction too. We build FlipTest, a three-level hierarchy of increasingly strict tests over 1,680 initial frames from 10 simulated and 15 real-world tasks. At the base, visual minimal pairs, two nearly identical frames whose true futures differ, test whether predictions change across the boundary; matched controls go further and test whether they change only where the future does; and dense sweeps, the strictest level, locate exactly where they change. All 11 video world models we evaluate fall short. The best averages 18.3% pair accuracy over real and simulated scenes, below the 25% of random guessing. Models flip as often on steps that leave the future unchanged as on steps that change it, and their response stays flat across the sweeps. On the same frames, a vision-language model is selective and traces a near S-shaped curve near the boundary, and a coding agent that measures the image comes close to the true boundary. This implies that the deciding information is in the frame, and video models just miss it. We therefore urge the community to rethink world modeling as pure video prediction. Next-frame prediction must do more than draw plausible pixels; it must also identify the causal states that control future dynamics.
https://arxiv.org/abs/2611.19822
In 2025, there was a total of 358 weather-related disasters worldwide affecting millions of people. For unmanned aerial vehicles (UAVs) to autonomously aid these people, they need to be able to navigate around complex obstacles and reach their destinations to deliver supplies or quickly locate survivors in disaster-stricken areas. Our research addresses this need by providing a method to compute minimum-time trajectories in real time while providing guarantees of obstacle avoidance along the trajectory. Previous approaches treat the problem of computing time-optimal trajectories without considering obstacle avoidance. Our work not only includes obstacle avoidance constraints, but also improves overall mission time for navigation. We define mission time as the sum of planning time and traversal time. In time-sensitive emergencies, rapid trajectory planning is essential to ensure the prompt delivery of critical medical aid. As such, we consider the combined planning and traversal time as the key metric for how quickly the vehicle can reach a survivor. We show a sample mission in Fig. 1 where the quadrotor navigates through multiple canyon-like obstacles to deliver aid; during most of this trajectory, it is applying the near-maximum thrust.
https://arxiv.org/abs/2611.19818
Experiments near vehicle handling limits must keep three questions apart: what a maneuver requests, what the closed-loop system executes, and whether the task is completed. We present DynLimit, a simulation platform that organizes this process end to end. Scenarios are composed from road, friction, obstacle, and reference objects; planners and controllers attach through a shared observation and control interface; a vehicle adapter runs either a license-free four-wheel model or an external dynamics solver; and synchronized records feed task evaluation, replay, and response inspection. The platform carries a task-oriented evaluation method that pairs a prescribed reference demand with a sampled passing set and event-aligned diagnosis. Across eight task families, three friction environments, and three reference-assisted baseline chains we executed 450 runs: 360 nominal, 18 locally refined, and 72 with prescribed initial offsets. Method differences depend on the task family, equal aggregate pass counts arise from different passing cells, and local refinement narrows two sampled transitions without locating a continuous boundary. Two case comparisons show why sideslip or tire-utilization peaks cannot replace task constraints. The three views therefore stay distinct in every reported run: an outcome can be traced from the prescribed demand, through the executed response, to the task rule that decided it. Code is available at this https URL
https://arxiv.org/abs/2611.19785
Safety-critical high-speed legged locomotion requires motion planners to balance safety foresight with online computational efficiency. Although short prediction horizons reduce rollout costs, they provide limited safety foresight, and strict safety constraints severely restrict the feasible trajectory space. We propose a recovery-guided model-based diffusion (MBD) framework for safety-critical legged locomotion. It incorporates a learned terminal recovery critic into short-horizon trajectory optimization. Specifically, the critic approximates the worst-case future clearance margin along rollouts of a designated recovery policy. We introduce a feasibility-guided refinement strategy that combines within-horizon constraints and terminal recoverability at each sampling stage, while retaining feasible elites to mitigate sampling-support loss. Across 50 paired randomized Unitree Go2 obstacle-avoidance trials, our approach achieves zero collisions and 98% strict-clearance success, while requiring substantially less computation than long-horizon MBD baselines. A project page is available at this https URL.
https://arxiv.org/abs/2611.19775
Joint-embedding predictive architecture (JEPA) world models predict future embeddings instead of pixels and plan in latent space. Two challenges remain: 2D images leave the metric geometry that manipulation acts on implicit and entangled with appearance, and what these models imagine stays hidden, as they are mostly judged in simulation by short-horizon latent planning. We present JEPA4R, a JEPA world model that observes single-depth-camera point clouds, predicts and plans in their latent space, and acts through a policy head on its frozen latents; we call this 4D point planning. A decoder on the frozen world model shows what it imagines as 4D point clouds, with a mean point error within 1.1 cm over 200 steps. Under the policy-learning protocols of OGBench and CortexBench, JEPA4R leads pixel JEPA models on OGBench Cube-Single, Cube-Double, Cube-Triple and Scene, and ranks first on MetaWorld and Adroit Relocate with 98.4% and 88.0%, above the runner-up, R3M, at 96.0% and 65.3%. Trained only in a digital twin, JEPA4R and its policy heads run zero-shot on the real arm with both a gripper and a dexterous hand.
https://arxiv.org/abs/2611.19771
Water--land cross-domain robots require continuous localization across land, transition and underwater phases, where sensor characteristics and availability change abruptly. Existing datasets and conventional metrics are not designed to capture transition-induced degradation and failures. We present \textbf{M-CROSS}, to the best of our knowledge, the first multisensor simulation dataset and benchmark for SLAM across continuous water--land transitions. It provides synchronized LiDAR, sonar, stereo camera, IMU, DVL, and depth measurements; 6DoF pose ground truth; sensor-wise medium-state annotations; and medium-dependent sensor degradation models. We establish a transition-aware protocol comprising the Trajectory Completion Rate (TCR), Piecewise Absolute Pose Error (PW-APE), Transition End Error (TEE), and Transition Survival Period (TSP), which measure trajectory completion, single-domain accuracy, transition-induced error, and localization survival under prolonged partial immersion, respectively. Experiments with 6 representative SLAM systems show that existing methods fail to maintain both localization accuracy and trajectory continuity across the full set of water--land transitions, exhibiting transition-induced drift, trajectory discontinuities, and tracking failures. M-CROSS is publicly available this https URL
https://arxiv.org/abs/2611.19765
A distributed multi-robot object transportation strategy is proposed for objects of unknown shape, size, geometry, mass and mass distribution without any prior knowledge about the object or number of robots involved in the transportation process. Robots follow the boundary of the object and dynamically determine viable pushing points. A novel object-model-free heading-error-driven pushing effort regulation method is proposed to promote goal-directed object motion; robots regulate their pushing effort using individual and collective heading errors. Robots dynamically relocate around the object boundary if a pushing point is lost or the required pushing effort exceeds its capability to correct its heading. The proposed method is validated using simple and complex shapes with convex and non-convex boundary regions and dynamically changing weight distribution of objects. Detailed analysis on the effects of robot distribution and initial object pose on the transportation performance in terms of required time and path efficiency is also presented. Scalability analysis revealed that object transportation time is dependent on the number of pushing surfaces available which in turn depends on the object size, shape, and set inter-robot safety distance. The proposed system yielded highly efficient object paths with consistent elapsed transport times over several trials robust to external disturbances such as non-uniform friction between contacting surfaces and robot wheel slip.
https://arxiv.org/abs/2611.19731
Progress in autonomous navigation in off-road environments requires not only advances in algorithms, but also robust and capable physical platforms suited to both development and deployment. Today, off-road autonomy is typically developed and tested at one of two extremes of vehicle scale, each with different drawbacks. Full-size vehicles are capable but expensive, require large logistic infrastructure for deployment and maintenance, and expensive when pushed beyond their limits. RC-scale vehicles are small and inexpensive, but limited in the terrain they can traverse and the payload that they can carry, which includes their sensors and compute. We present the AlphaTruck platform, which leverages recent advances in compact sensing and compute to integrate multimodal sensing, embedded CPU-GPU compute, and an onboard autonomy stack for high-speed, off-road navigation, all integrated into a large-scale, 1/5th RC vehicle chassis. AlphaTruck is designed as both a research testbed and a field-deployable platform for commercial and defense missions such as survey, search and rescue, and agriculture, with the capacity to carry task-specific payloads. At 1/5 scale, the autonomy stack, sensors, and batteries all compete for the same mass, power, and cooling budget, so the platform must balance five needs: mobility over rough terrain, rich sensing, onboard computation, payload capacity to carry the autonomy stack while leaving room for task-specific equipment, and practical operation and repair. Thus, AlphaTruck navigates off-road environments autonomously at 6-10 m/s using only onboard sensing and compute.
https://arxiv.org/abs/2611.19730
Although object-goal navigation (ObjectNav) approaches are usually evaluated in simulation, which offers scale and repeatable environments, real-world deployments are rarely examined beyond feasibility demonstrations. This paper presents the deployment of Room-Mediated Co-occurrence, an ObjectNav policy that reasons over Room Probability Vectors (RPVs), on two robotic platforms (Boston Dynamics Spot and Clearpath Robotics TurtleBot 4) through a robot-agnostic ROS 2 bridge. We study how these semantic priors generalise to physical environments and describe the adaptations required to transfer RPV from simulation to hardware, covering sensing, localisation, and the action interface. Across 66 trials on Spot, searching for 11 object categories from two starting positions in a university postgraduate research facility, RPV achieves a raw Success Rate (SR) of 0.455. Our analysis identifies undetected glass walls, entry into off-limits areas, limited usable depth range, target size, and mismatch between the room lexicon and physical layout as plausible contributors to the 8.4 percentage-point gap between the real-world SR and the reported simulated SR of 0.539. Code is available at this https URL.
https://arxiv.org/abs/2611.19720
Flow-matching robot policies generate each action chunk through repeated network evaluations, one per denoising step. Cross-cycle caches such as C$^3$ache reuse computation from earlier replanning calls, but whether they beat simply taking fewer steps is unclear. We compare the two in Fast-WAM, a 6B-parameter world action model, on LIBERO-Goal. Two uncached steps keep the success of ten: on all 500 initial states they are non-inferior within two percentage points, for one checkpoint and noise seed. Under PyTorch's default compile mode, they also cut a replanning call on an RTX A6000 from 202 to 92 ms. This leaves little room for caching. A cache that keeps two fresh steps cannot be faster than two uncached steps: every call still encodes the images, runs the video expert and computes those two steps. Caching the first of two steps, refreshed every fourth call, saves at most 11--14% of a call by our cost model. Cached policies are also fragile. Their losses tracked the share of the flow path the cached steps cover: under Fast-WAM's current time shift, C$^3$ache's eight cached steps cover 80% of the path instead of 44%, and the cached policy succeeds on 63% of states against 95% uncached. Resampling the noise on every call cost caches covering 60% or more of the path 14--40 points. These results argue for fewer-step baselines and for testing reuse under the deployed sampler and noise settings. We release our evaluation harness, logs and a checklist.
https://arxiv.org/abs/2611.19709