Simulation benchmarks are a useful way to measure progress in robotics; typically they provide success rate as the dominant measure of performance. However, success rate reports only whether a rollout completed the task, hiding by what margin it succeeded, how sensitive the success is to goal parameter changes, requirements it may have violated, and whether success persisted. Signal Temporal Logic (STL) provides a formal language for capturing specifications; it can be used to define requirements, and measure how close a robot behavior is to satisfying or violating them. Using STL monitors in a simulator, however, requires exposing simulator state and mapping it to specification-relevant signals. We present Specola, a tool for evaluating robot behaviors in simulation with respect to STL specifications. Specola provides an interface for writing specifications over simulator signals, and creates and manages the relevant monitors while a policy executes. We provide a Python API and command-line interface for integrating monitoring into existing policy execution loops. We provide an adapter interface for connecting new simulators, and provide adapters for nine simulation environments and benchmarks, including LIBERO, RoboCasa, Isaac Lab, and RoboDojo. We provide case studies that illustrate the nuanced evaluation that Specola enables. Code and adapters are available at this https URL.
https://arxiv.org/abs/2610.35730
Vision Language Models (VLMs) have shown impressive capabilities in high-level reasoning and task planning for robots. However, specialized domains remain a challenge for VLMs' image interpretation and grounding abilities. We introduce TrySee, a modular closed-loop robot task planning pipeline integrating general-purpose VLM reasoning with domain-specific perception and established robotics components. The system consists of an inherently reactive cyclic planning pipeline, augmented with domain-specific modular vision preprocessing, to provide online grounding. Finally, a dynamic preprocessing selection mechanism contributes to the scalability of the pipeline. The system requires neither VLM fine-tuning nor end-to-end demonstrations and adapts through replaceable perception modules and motion planning. The approach is evaluated on planning tasks across 5 widely different domains, including a real-world robot disassembly task. The field tests in a brownfield environment demonstrate the approach's practicality in integrating VLM planning into specialized robotic systems with limited domain-specific training data.
https://arxiv.org/abs/2610.35687
Large Language Models (LLMs) are widely adopted for reflective error correction in task planning; however, existing approaches primarily rely on autonomous exploration, rendering them prone to accumulating erroneous experiences during early interactions with new environments. To address this limitation, we propose the Flexible Instructional Scaffolding Reflection Framework (FISRF), an agent--mentor architecture that estimates the robot's Zone of Proximal Development (ZPD) in task planning and adaptively selects reflection strategies and mentor guidance, thereby facilitating the accumulation of effective error-correction experience. Experiments in ALFWorld and on real-world robotic platforms demonstrate that FISRF reduces the average number of error-correction rounds by 37% and redundant reasoning by 25.1%, while improving the overall task success rate by 8%. Project webpage : this https URL
https://arxiv.org/abs/2610.35686
Agile quadruped navigation in dynamic environments demands trajectories that are both dynamically feasible and provably collision-free. Most real-time planners achieve tractability through a convex reduction that requires simplified kinematic models, discarding motion that the robot can readily execute, and certify safety only at discretization points, leaving open possible inter-sample collisions with moving obstacles. We present a real-time motion planning framework that retains the fully-actuated $SE(2)$ model of a quadruped, with its anisotropic, heading-coupled velocity bounds, and accepts the resulting nonconvexity. By parameterizing trajectories as composite Bernstein polynomials, we exploit the convex hull property to certify collision avoidance and the input bounds over the entirety of each planning horizon. Solved at online replanning rates, the optimization runs in closed loop, commanding body velocities to the locomotion controller. We validate the approach in simulation against ablations and external baselines, and in hardware experiments on a quadruped navigating among unknown moving obstacles, recovering both lateral and heading-coupled motion that simplified models exclude.
https://arxiv.org/abs/2610.35670
Robot corrections allow people to adjust a robot's behavior, but a single correction changes many features. Also, preferences about object attributes and relationships between objects cannot be expressed by moving the robot. We propose environment edits as a complementary form of feedback. The robot's motion is held constant as the human edits the scene, so the only explanation for the edit is the moved object. We introduce Feature Learning from Environmental and Robot-Relational Edit Traces (FERRET), which learns preferences from both robot and environment corrections. We show that environment edits are able to disambiguate features and learn preferences that robot corrections alone cannot.
https://arxiv.org/abs/2610.35659
Visual Place Recognition (VPR) is an important means for loop closure detection in visual Simultaneous Localization and Mapping (SLAM). While state-of-the-art VPR and SLAM approaches excel in urban and feature-rich natural environments, the vast and feature-poor environments of extraterrestrial surfaces like on the Moon or Mars pose severe challenges for existing approaches. This paper presents a novel benchmark, VPR-Space, to evaluate VPR capabilities on extraterrestrial surfaces. There are three contributions: (1) We collected sixteen VPR database-query datasets based on existing data from Space Analog Domains (SAD), terrestrial environments that resemble properties of the Moon or Mars. The collection includes a range of challenges regarding environment, viewpoint change, and illumination conditions. (2) To address the ill-posed nature of VPR, we propose a novel approach to generate the ground-truth information in VPR benchmarks. Instead of defining that a query and datbase image show the same place if and only if their camera poses are within fixed position and viewing direction thresholds, we propose to make the decision dependent on whether the match would be valuable in the downstream SLAM task. To avoid the overhead and restrictions of evaluating VPR in-the-loop within SLAM systems, we provide VPR ground-truth (GT) matrices based on the performance of an ensemble of state-of-the-art Relative Pose Estimators (RPE). Under this GT we require a VPR method to identify exactly those image pairs for which a subsequently applied RPE is expected to provide a valuable pose estimate in a SLAM context. (3) We evaluated nine state-of-the-art VPR approaches. The results show considerable room for improvement and indicate directions for future research. We provide a pre-release version of the dataset on github: $\texttt{this https URL}$
https://arxiv.org/abs/2610.35642
Latent world models are typically pre-trained offline and kept frozen at test time, so planning with them can degrade under distribution shift. Test-time adaptation (TTA) can mitigate this degradation by updating the model during deployment. Unlike pre-training on fixed data, TTA for planning is closed-loop: the planner uses model rollouts to select actions, and the resulting transitions drive the next update. This raises the question: which objective should guide TTA for planning? Under a prediction-only objective, the model is fit only to the outcomes of its own actions, so it can remain wrong about the actions that would reach the goal, and low prediction error need not translate into better planning. Inspired by reward-biased maximum likelihood from adaptive control, we introduce Optimistic Test-Time Adaptation (OpTTA). Its objective has two terms, the prediction loss on observed transitions and the planner's goal-reaching cost on its candidate rollouts, both minimized over the model parameters. The planning term biases adaptation toward models that are optimistic about reaching the goal, without any additional environment interaction. Across visual and environment shifts on manipulation, reaching and navigation tasks, OpTTA raises final planning success over the frozen model by 13.5 percentage points on average, compared with 6.9 for the prediction-only objective (AdaJEPA), when only the predictor is adapted. When the encoder is adapted as well, the gains are 13.5 and 7.5 points. These experiments span three JEPA world models with different encoders and training objectives and, for temporal straightening, both CEM and gradient-based planners. Our results suggest that test-time adaptation of world models for planning benefits from an optimistic, task-aware term in addition to the prediction loss.
https://arxiv.org/abs/2610.35636
In autonomous driving, robot teleoperation serves as a critical safety fallback mechanism, requiring operators to assume direct control in the event of system failure. While recent research has pivoted toward high-level supervisory control or simulation-based studies, these approaches often fail to capture the physical dynamics and sensory demands of driving a full-scale vehicle. To address this gap, we evaluated the impact of spatial data representation on operator performance using a real car-sized vehicle in a field experiment with $N = 18$ participants. We compared three visualization interfaces: (i) a standard camera feed baseline, with two bird's-eye views (BEV) from (ii) a raw LiDAR point cloud, and (iii) a sensor fusion of LiDAR and camera data streams. Contrary to prior passive observation studies suggesting that sensor-fusion BEV may hinder awareness, our active-control results demonstrate that such representation significantly outperforms the standard LiDAR BEV in perceived usability ($p \leq 0.0001$) and cognitive task load ($p = 0.01$, NASA-TLX score: 34.58/100) while also being significantly better than the Camera-only view ($p = 0.043$). The fused interface also led to statistically significant reductions in task completion time ($p = 0.0461$) and superior usability (SUS: 77.9/100) compared to those of the Camera-only and LiDAR-only views. By synthesizing objective performance data with comprehensive subjective assessments, we demonstrate that BEV fusion maximizes safety margins while minimizing the operator's mental demand. These findings challenge existing teleoperation conventions and provide an empirically validated approach for designing robust remote piloting systems.
https://arxiv.org/abs/2610.35630
This work explores a multimodal approach to the alignment of the behavior of open-ended learning autonomous robots with human purposes through the use of large language models as cultural enablers. While autonomous robots can generate their own skills and goals through interaction with the environment, they often lack mechanisms to ensure that these remain relevant and aligned to those of human users. The proposed approach makes use of the general and cultural knowledge contained in LLMs and VLMs to establish a multimodal interactive alignment process in which human purposes, expressed in natural language, are transformed into motivational components of a robot architecture in the form of robot missions and drives that guide the behavior of the robot. The system is structured into three layers for semantic alignment, mission generation, and drive modeling. This design enables a bidirectional interaction loop: human inputs define high-level purposes, robots expand them into executable missions making use of multimodal information relayed by LLMs and VLMs, and feedback maintains alignment with human intent. Experiments in simulation and with a physical robot demonstrate that the process produces valid missions and behaviors, supporting effective human-agent alignment in interactive scenarios with autonomous robots.
https://arxiv.org/abs/2610.35629
Efficient robotic data collection remains a major bottleneck for vision-language-action (VLA) policy learning, especially for tasks requiring accurate end-effector positioning and camera-action alignment. This challenge is particularly severe in electronic-waste disassembly, where robots operate in cluttered assemblies of densely packed, visually similar components. Full digital-twin simulation is difficult because many parts are thin, reflective, or mechanically complex, making accurate object-level meshes and contact models difficult to obtain. In this work, we focus on pre-contact reaching and propose a 3D Gaussian Splatting (3DGS)-based data generation pipeline for wrist-camera VLA adaptation. Our method reconstructs the real workspace with 3DGS and renders diverse wrist-camera observations from robot-aligned poses. These observations are paired with smooth, structured reaching trajectories to provide robot-aligned visual-action supervision for VLA fine-tuning. We further augment the VLA policy with an instruction-conditioned reach verifier that estimates target proximity and provides reliable termination before physical interaction. Experiments in motherboard disassembly demonstrate precise VLA-based reaching using wrist-camera observations alone, without an external side-view camera. With $\pi$0.5, 1,500 generated trajectories achieve 80.0\% precise-reaching success across three targets, compared with 58.7\% using 150 teleoperated demonstrations, while requiring less than 10 minutes of active human capture. Project website: this https URL
https://arxiv.org/abs/2610.35626
Expressive robot motion positively impacts human-robot interaction by improving user engagement, likability, or task performance. We present a novel approach to automatically generate and modulate complex, expressive full-body gesture sequences from a multimodal (text, audio, video) context description. Based on a unified mathematical implementation of the Principles of Animation using Dynamic Movement Primitives, we use multimodal foundation models to generate such sequences along with parametric motion variations that are highly context-aware. This method extends the state of the art in terms of flexibility and generality by being interpretable, composable, and working across different robot morphologies. Moreover, we integrate the system into a continuous control framework and leverage knowledge distillation to learn a much smaller model, significantly improving token efficiency and system latency. Results from a user study with a human-like platform indicate that participants judged our system's motions to be better aligned with the interaction context than motions produced under a non-modulated or API-level condition. We also demonstrate how the system generates expressive motion for robots with different kinematics, showcasing its versatility. Paper webpage: this https URL.
https://arxiv.org/abs/2610.35615
Generalist robot policies and language-model agents provide complementary capabilities, but completing a task also requires adapting their use to the consequences of physical interaction. We study execution as a locus of adaptation: feedback guides the current action and supplies evidence for revising subsequent decisions under fixed model weights. We introduce RoboDoctor, a training-free framework that connects diagnosis, grounded action, and persistent experience across three revision targets. The harness allocates control between policy and agent; intervention determines when to assist while preserving useful policy behavior; and operation refines physical methods through observed effects. Linked experience records retain the reason for a decision, the attempted method, its outcome, and conditions for reuse. On a curated archive of 54 RoboDojo-Sim task entries, RoboDoctor achieves a five-dimension mean score of 57.10, with a native success rate of 49.44%. Recorded interactions illustrate strategy changes, selective correction, and grasp revision. These findings characterize execution-time adaptation in the evaluated system; controlled trials remain necessary to isolate the contribution of cross-episode experience.
https://arxiv.org/abs/2610.35604
Coordinating many miniature robots in a confined arena, with no leader, central planner, or global map, is a core challenge for swarm robotics. As the swarm grows denser, collision avoidance becomes the limiting factor, and the number of safely coexisting robots depends on the formulation of the inter-robot safety constraint. We present a distributed predictive flocking controller in which each robot solves its own nonlinear model predictive control (NMPC) problem, optimizing swarm cohesion and alignment costs, inter-robot and obstacle safety, and a task objective, while exchanging only predicted trajectories with local neighbors. Within this generalized controller architecture, solved in real time, we compare six barrier and control-barrier-function (CBF) safety formulations on a digital twin of an open-source vibration-driven bristlebot in a $0.64\,\mathrm{m^2}$ arena. A look-ahead discrete-time CBF performs best overall, with the fewest collisions and the widest inter-robot margins across nearly every swarm size tested. We deploy it on phototaxis, phototactic orbiting, and cohesion without a stimulus tasks, using swarm sizes starting from ten robots and up to the geometric packing limit. The swarm holds well: collisions stay low in small swarms, rising steeply as the packing limit approaches, while coordination and cohesion degrade gently rather than collapsing. The swarm is found not to trade safety for order, keeping both across the confined arena, with local alignment high at every swarm size.
https://arxiv.org/abs/2610.35582
Long-horizon embodied navigation may be interrupted by a higher-priority instruction before the current task sequence is complete. The agent must finish its current atomic task, execute the inserted task, and resume the remaining sequence from the updated environment state, where its viewpoint and available navigation candidates may have changed. To evaluate this capability, we introduce PIFR benchmark, a novel task for runtime task preemption and resumption in embodied navigation. PIFR includes single, repeated, and nested interruption settings,with stage-specific metrics for inserted-task completion, resumption of the original task, and completion of the full sequence. Evaluations show that recovery performance varies across interruption conditions, while aggregate success can obscure differences in interruption handling and resumption. We further propose a lightweight candidate-ranking baseline to improve target re-grounding after interruption. Together, PIFR and the baseline provide a systematic framework for studying interruption handling and task recovery in long-horizon embodied navigation.
https://arxiv.org/abs/2610.35576
Experts can master fine hand-object manipulation skills, yet limited conscious perception of rapid tactile interactions hinders their ability to articulate the underlying control mechanisms. Badminton racket control requires rapid, fine hand-force coordination, providing a demanding testbed for uncovering these mechanisms. An 864-node tactile-inertial glove with synchronized 100-Hz acquisition recorded over 14,000 strokes from more than 70 participants across five skills. Inspired by sensorimotor control, our mechanics-grounded two-layer framework inferred object-driving and grip-stabilizing control from tactile history, while resolving their spatiotemporal force realization. We found that higher proficiency was associated with selective rather than extensive control: greater skill specificity, anticipatory regulation, focal distal modulation and lower geometric torque cancellation, while spatiotemporal coordination showed a non-monotonic acquire-refine pattern. We translated these mechanisms into personalized guidance targeting force control and force-motion coordination. In a randomized cohort, mechanism-guided learners gained 0.72 expert-rated skill levels versus 0.05 with level-only feedback, making control mechanisms actionable.
https://arxiv.org/abs/2610.35563
Training robotic manipulation policies in simulation is widely adopted due to safety and cost efficiency; however, tasks involving obstacles remain under-performing and often converge slowly under Deep Reinforcement Learning (DRL). To address this challenge, we propose a task decomposition framework for DRL that integrates Transfer Learning (TL) with Reward Redesign (RR) to improve learning efficiency and robustness in obstacle environments. The TL strategy selectively transfers only the first-layer critic parameters across structurally related tasks, since that layer captures general state--action representations while deeper layers encode reward- and obstacle-specific value geometry; RR decomposes tasks into staged sub-objectives to provide denser optimization signals. Experiments on the PyBullet Panda platform show consistent gains in obstacle settings. On Push with obstacle, our method achieves $0.83 \pm 0.05$, outperforming the strongest baseline (Truncated Quantile Critics (TQC), $0.77 \pm 0.06$) by approximately $7.8\%$. On Slide with obstacle, performance reaches $0.95 \pm 0.02$, exceeding Soft Actor-Critic (SAC) ($0.84 \pm 0.06$) by about $11\%$ success rates. In addition to higher final performance, forward transfer reduces convergence time by up to $70\%$ in obstacle tasks, and RR shortens sparse-reward Pick-and-Place training from roughly $0.75$M to $0.20$M steps ($\approx73\%$ reduction). The best policy is deployed on a real Franka Emika FR3 robot as a qualitative feasibility demonstration.
https://arxiv.org/abs/2610.35494
Existing manipulation data collection methods typically offer either accurate robot-state acquisition through kinematic-chain-based teleoperation or convenient, portable operation through vision-based approaches. We present DEX-PHD, a portable handheld device that combines these advantages for dexterous manipulation by integrating a dexterous robot hand, continuous per-finger control, and multimodal logging. The system records proprioceptive information, fingertip contact data, and wrist-camera video, while the operator directly controls the robot hand through joint-level mapping. Its untethered design enables data collection across diverse environments. We demonstrate DEX-PHD on contact-rich tasks requiring coordinated multi-finger manipulation and deploy the collected demonstrations through open-loop replay on a physical humanoid robot. The results show that open-loop replay preserves the main temporal patterns of finger motion and task-relevant contact. Therefore, DEX-PHD provides a practical platform for portable, multimodal dexterous manipulation data collection.
https://arxiv.org/abs/2610.35462
Data-enabled predictive control has recently emerged as a promising control paradigm, enabling a transparent optimal-control formulation without the need to learn an explicit dynamics model. This paper presents a number of extensions paving the path towards its use in real-time robotics tasks. Following recent work, we utilize a nonlinear predictor based on Gaussian kernels to represent the relationship between input and output data. We propose a damped Gauss-Newton method that enables real-time control by efficiently exploiting the least-squares structure of the control problem. In addition, we introduce a hybrid buffer management strategy that incorporates informative online data while retaining relevant offline data, allowing the predictor to account for changes in the dynamics. We demonstrate the tracking performance and computational suitability of the proposed method in MuJoCo using a Franka Research 3 arm pushing a block across surface, without prior knowledge of its changing friction values.
https://arxiv.org/abs/2610.35458
End-to-end driving models perform well on standard benchmarks but collide frequently in safety-critical scenarios. We present a failure-mode analysis on NeuroNCAP which shows that 95.9% of DiffusionDrive's collisions are planning failures despite reliable detection, pinpointing the bottleneck in planning rather than perception. We attribute this to a fundamental data imbalance, as safety-critical interactions are rare in real driving logs, so planners are hardly ever trained on them. We close this gap with a novel model-aware framework that generates safety-critical training scenes against a specific planner. Each planner is attacked at the bird's-eye-view (BEV) level through a differentiable surrogate distilled from its own planning head. This keeps the expensive video renderer out of the attack loop. We extract 50 scenes per planner, each pairing an attack with a safe escape trajectory that serves as the fine-tuning label. A fully automated quality-diversity search generates both the attacks and the escapes, so that their variety is not specified by hand. Only these scenes are rendered to fine-tune the planner, which reduces the computational cost significantly. Fine-tuning on these scenes roughly halves the closed-loop collision rate of two planners on NeuroNCAP (SparseDrive 28.0% to 12.2%, DiffusionDrive 37.5% to 19.2%) while largely preserving normal driving. A cross-planner transfer experiment shows that the gain comes from targeting the specific planner. Each planner improves most on the scenes generated against itself, and DiffusionDrive fine-tuned on SparseDrive's scenes retains only 6.7 of its 18.3-point collision-rate reduction.
https://arxiv.org/abs/2610.35448
Multi-robot teams executing predefined missions must adapt to runtime changes and sustain mission management despite robot failures. This paper proposes MATE-BT (Mission, Allocation, and Task Execution with Behavior Trees), a hierarchically decentralized framework that separates mission execution, allocation, and task execution. An active onboard leader manages mission progression and team-level task assignment, with authority transferable to another leader-capable robot after failure. Interchangeable decentralized methods resolve target assignments, while each robot adapts its local behavior through planning and acting with behavior trees. Webots simulations and real-robot experiments demonstrate mission continuity despite new targets and robot failures, including active-leader failure. In the physical experiments, all MATE-BT computation runs onboard. Hardware-in-the-loop resource measurements further support onboard execution on Jetson Orin Nano and Raspberry Pi 5. By updating only the affected layers without full-plan regeneration, MATE-BT maintained a response time of approximately 130 ms with 30 robots and 120 targets. Comparisons of four target-assignment plugins reveal scenario-dependent trade-offs between mission completion time and total travel distance.
https://arxiv.org/abs/2610.35429