arXiv_RO
-
Adaptive Prescribed Performance Trajectory Tracking for Uncertain Autonomous Underwater Vehicles With Input Saturation
2026-10-14 21:29:25Athanasios K. Gkesoulis, Christos Vlachos, George K. Fourlas, Charalampos P. Bechlioulis, George C. KarrasAbstract
Accurate trajectory tracking is essential for autonomous underwater vehicles operating with uncertain hydrodynamics and limited thruster authority. This paper develops a low-complexity adaptive prescribed performance controller for uncertain underwater vehicle dynamics with coupled and saturated inputs. The proposed method adapts the performance functions directly through the mismatch between the requested and saturated control inputs, enlarging the performance funnels only when the available actuation cannot meet the nominal specifications. A coupled invariant-set analysis establishes boundedness of all closed-loop signals, prescribed bounds on the filtered tracking errors, and explicit feasibility conditions. Comparative simulations on a BlueROV2 underwater vehicle show that the adaptive design maintains prescribed performance during a figure-eight maneuver, whereas conventional prescribed performance control loses feasibility under input limits. A real-time pool experiment further demonstrates stable trajectory tracking and the practical implementation of the proposed method on an underwater robotic platform.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20957
PDF
-
LEAP: Gradient Flow Augmented Lagrangian Trajectory Optimization for Contact Constrained Robots
2026-10-14 21:04:31C\'esar E. Ramos Chuquiure, Ryan Tsai, Yutong Zhou, Zihang Huang, Vansh Thakur, Akshunn Trivedi, Zachary Lin, Pearl Lin, Ruikai Yang, Challen Enninful Adu, Ram VasudevanAbstract
Generating dynamically feasible motions for legged and manipulating robots requires solving a large, nonlinear, non-convex optimal control problem (OCP) in which contact wrenches must satisfy friction-cone constraints throughout the motion, not only at isolated instants. Existing solvers are sensitive to the initial guess and scale poorly with the number of joints. This paper introduces LEAP, which transcribes the OCP with pseudospectral collocation and, instead of a Newton or SQP solve, integrates a primal--dual gradient flow of a Powell--Hestenes--Rockafellar augmented Lagrangian to compute a solution. Because the flow is stiff, this paper designs a linearly implicit integrator with a Gauss--Newton metric, momentum, and a merit-based step controller that keeps the augmented Lagrangian monotone. Across locomotion benchmarks on five robot platforms, from planar hoppers to 32-joint humanoids, LEAP is the only method to solve every tested problem, achieves substantial speedups over Crocoddyl and Aligator on several benchmarks, and reaches trackable references at smaller compute budgets. The resulting trajectories are validated by tracking them in a high-fidelity simulator and on hardware. We will make the code public upon final acceptance of this paper.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20936
PDF
-
Planning to Learn: Real-Time Robust Adaptive Control on the GPU with Guaranteed Future Learning
2026-10-14 20:55:10Anutam Srinivasan, Siddhant Panse, Glen ChouAbstract
Robust adaptive control is vital for keeping robots safe while actively reducing uncertainty in unfamiliar settings. However, traditional methods are often conservative since they fail to account for guaranteed future parameter learning during planning and struggle to scale to high-dimensional systems. In this work, we present A-SLS, a learning-aware robust adaptive model predictive control (RAMPC) framework based on system-level synthesis. A-SLS forecasts future parameter uncertainty and preserves correlations between process disturbances, parameter error, and estimate updates to construct tight, guaranteed reachable sets that account for future information gain. We also develop a GPU-accelerated A-SLS solver to enable real-time performance. Across nonlinear robotic systems, A-SLS reduces reachable-tube conservativeness, maintains real-time performance, and scales to whole-body control for a quadruped with 61 states, 8 uncertain parameters, and 12 control inputs. We further demonstrate the approach on hardware, where a physical Crazyflie drone learns an uncertain dynamics parameter online to stabilize on the fly.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20925
PDF
-
BubbleCBF: Constructive Safety for Second-Order Systems and Application to Autonomous Robot Navigation in Unknown Environments
2026-10-14 20:24:47Mani Amani, Mohammed Alyaseen, Zhirui Dai, Ki Myung Brian Lee, Nikolay Atanasov, Jorge CortesAbstract
Satisfying safety constraints for systems with second-order dynamics is challenging because a position constraint may require infeasible deceleration. Higher-order control barrier functions (CBFs) provide an approach for expressing safety conditions for such systems but feasibility depends on the system dynamics and available control authority. We develop a constructive approach for designing feasible safety constraints for second-order control-affine systems. Starting from a signed distance function (SDF), we construct collision-free spheres, i.e., bubbles, in position space, and use their quadratic geometry and overlap to construct a velocity-dependent safety constraint. The associated safe set is represented as a union of intersections and enforced through a quadratic-program safety filter. Under mild assumptions on the dynamics, bubble overlap, and design parameters, we prove that the quadratic-program-based controller is well defined, continuous in the system state, and renders the set forward invariant. We also derive sufficient conditions for feasibility under bounded inputs. We demonstrate that our BubbleCBF, applied to a differential-drive robot, achieves safe autonomous navigation in unknown environments. Videos and results are available at: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20895
PDF
-
Optimally Trading Energy for Information through Speed Trajectory Optimization of Sustainably Powered Mobile Robots
2026-10-14 20:06:11Kavin M. Govindarajan, Dimitra Panagou, Chris VermillionAbstract
Sustainably powered mobile robots enable long-duration observational missions by harvesting energy from the environment. However, effective autonomy requires the robots to make decisions as to how to allocate this energy to maximize information quality over time. In this paper, we study a persistent (infinite-horizon) speed trajectory optimization problem that is posed as a periodic optimal control problem in which a robot repeatedly traverses a fixed closed path, coupling a super-linear propulsion cost with dynamic information gain and decay. Using the information-theoretic quantity of clarity as an information metric, we first derive the necessary conditions for optimal control. We then derive a number of specialized follow-on properties, which characterize (i) the nature of the optimal control when points on the path are of varying importance and when they are of equal importance, along with (ii) a high-speed information limit that is approached when energy reserves approach infinity. We illustrate the information-optimal speed trajectories on a simple example in order to showcase key trends that are followed under the optimized speed profile. This is followed by a simulation study based on the persistent characterization of salinity in the Chesapeake Bay, illustrating the practical merit of applying the results from this work.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20875
PDF
-
Race to Recovery: Designing Advanced Safety Systems for Autonomous Driving via Learning Autonomous Racing
2026-10-14 20:04:54Teodor Ilie, Kleber Cabral, Sidney GivigiAbstract
Vehicles that lose control at the handling limit through icing, hydroplaning, or an abrupt evasive maneuver fall outside the operating envelope of production safety systems such as electronic stability control, which focus on preventing instability rather than recovering from it. Expert drivers regain authority in these conditions by drifting. Existing autonomous recovery approaches are validated on idealized scenarios, define "recovered" states empirically and inconsistently, or rely on offline-planned trajectories rather than acting online. We address these gaps by first training a racing policy with reinforcement learning that learns drifting as a time-optimal maneuver, then adapting it to recovery through continued training with a minimum-time reward. We define recovery relative to a phase-plane-grounded stable equilibrium and introduce Gym-Khana for controller training and evaluation. Across 294 initial loss-of-control states, the transferred policy improves recovery by 186.8% over a Stanley path tracker and outperforms both a nonlinear model predictive controller and a recovery-only policy trained from scratch, while also recovering faster on states the baseline can already handle. An ablation shows that racing pretraining, rather than broader initial-state exposure alone, drives this gain. Deployed on a physical 1:10-scale F1TENTH vehicle using system identification, actuator-lag modelling, and domain randomization, the transferred policy outperforms Stanley on every tested loss-of-control state, including recovering 50% of the time from a hard state the baseline never recovers from.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20873
PDF
-
Clarity-Driven Adaptive Mission Planning for a Solar-Powered Autonomous Surface Vessel
2026-10-14 20:00:27Kavin M. Govindarajan, Kaleb Ben Naveed, David Li, Devansh R. Agrawal, Mary Maceda, Matthew Bryant, Dimitra Panagou, Chris VermillionAbstract
This paper presents a comprehensive methodology, backed by simulation and experimental results, for an adaptive mission planning strategy that is mathematically grounded in the maximization of the information-driven quantity of clarity. In particular, the methodology introduced in this work addresses the use of sustainably powered autonomous surface vessels (ASVs) to perform scientific missions that prioritize locations of maximum interest. Because these locations of maximum interest are not known a priori but are rather identified based on in-situ measurements, online adaptation is essential for mission planning. Furthermore, the reliance on a limited-power renewable resource requires an adaptation strategy that maximizes information gathering subject to mobility restrictions imposed by the renewable resource. Our approach addresses these challenges through a clarity-driven ergodic search, where clarity represents a mathematical quantity that has been rigorously linked to differential (information) entropy. In our approach, a target clarity map is adapted online to reflect the prioritization of certain areas based on in-situ measurements, and an ergodic path planner continually re-plans based on the target clarity map and ASV speed limitations (driven by the renewable propulsion source). Focusing on a solar-powered ASV, we present simulations and experiments conducted at Jordan Lake, North Carolina, demonstrating the effectiveness of the proposed approach.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20871
PDF
-
A Phenomenology of Neural Geometry in Vision-Language-Action Models
2026-10-14 19:27:09Mozes Jacobs, Aiden Swann, Mathilde Papillon, Siddharth Boppana, Fenil R. Doshi, Usha Bhalla, Thomas Icard, Matt Feiszli, Thomas McGrath, Vasudev Shyam, Demba Ba, Leon Bergen, Nina Miolane, Owen Lewis, Jack Merullo, Ekdeep Singh Lubana, Atticus Geiger, Matthew Kowal, Thomas FelAbstract
Robotic manipulation is inherently geometric, but what shape does the world take inside the policy that performs it? Prior work on vision-language-action (VLA) policies establishes that task-relevant variables are linearly readable from activations, yet readability certifies only that a variable is present and says nothing about the shape its values trace, which may be curved and multi-dimensional. Using controlled sweeps, natural rollouts, linear probes, and activation interventions, we build a taxonomy of seven task-relevant concepts in VLA models. We find that realized geometry is predominantly multi-dimensional and is shaped by the constraints under which the policy acts. Physical joint limits, for example, leave wrist orientation an open arc rather than a circle, and distance to the target, a single scalar, is realized in two orthogonal subspaces, a coarse ruler for the approach and a fine ruler for the grasp. The same geometries reappear in two further VLA models on real-world robot data, indicating that they are neither model-specific nor artifacts of simulation. We demonstrate how the findings are actionable by steering along the geometry a concept realizes. Overall, this work lays out an initial phenomenology of realized geometry in VLA policies and demonstrates that a concept's shape carries as much importance as its readability.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20840
PDF
-
Persistent Profile-Guided Reset-Free Recovery Improves Final Gait Selection after Irreversible Leg Damage
Abstract
Damage-recovery algorithms often rank gaits from short trials, yet a gait that performs well briefly may not remain effective during continued execution. In reset-free recovery, each trial also changes the physical state inherited by the next. We introduce persistent profile-guided reset-free recovery (PGRR), which predicts multiple outcomes over repeated gait execution and uses conservative uncertainty-aware estimates to guide short online probes without resetting the robot. Across 108 matched MuJoCo tasks spanning leg amputation, distal fracture, and joint lock, PGRR improves final quality by 0.106 and slot-averaged recovery quality (SRQ) by 0.044 relative to an IT&E-inspired Gaussian-process baseline, while reducing low-quality failures by 27.8 percentage points. Final-quality gains occur in all three damage classes. Against no adaptation, PGRR also improves final quality and reduces low-quality failures, whereas the aggregate SRQ difference is inconclusive. Development ablations identify conservative uncertainty handling as the clearest supported contributor to the observed gains. These results show that PGRR can identify stronger post-damage gaits under continuous physical state and that final-gait quality and recovery-summary performance provide complementary evidence for evaluating reset-free recovery.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20838
PDF
-
Feasibility Ceilings Before Learning: Sizing and Timing Bounds for Drone-Mesh Interception
Abstract
A mesh of interceptors defending a fixed site must spread over the predicted arrival point of an approaching object. This is a recurring task in multi-agent robotics: N agents, each covering a disc of radius r, spread over a probability density so that a point drawn from it falls within some agent's disc. We give closed forms for the quantities that bound performance before any policy is chosen, and validate each by Monte Carlo. The uncertainty of a point predicted by extrapolating a noisy linear track follows from least-squares variance propagation plus a delta-method term for the uncertain arrival time, agreeing with simulation to within 1.8%. The coverage probability of a packed mesh admits a closed form accurate to 0.007 absolute, with a volumetric analogue. A naive area ratio misses a ceiling: while agents stay at least 2r apart, no mesh exceeds 90.69% coverage in the plane or 74.05% in a volume. This ceiling belongs to the separation constraint, not to the problem - permitting overlap substitutes Kershner's thinnest-covering density and removes it, the better regime above a crossover at p=0.80. Hexagonal packing is optimal among five arrangements; the centroidal-Voronoi configuration coverage control supplies reaches only half its coverage at small budgets. The Gaussian assumption is conservative under heavy tails and anisotropy but fragile under bias: a one-sigma aim-point offset costs 14 points of coverage. A repositioning team must also choose a commit time, and the admissible window can be empty. Against the applicable ceiling, analytic placement attains 85% of what the configuration permits while centralised PPO averages 15% over three trainer seeds, with a paired bootstrap against a null policy containing zero at every seed. We argue such ceilings should be computed before any learning experiment and quoted alongside every result.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20823
PDF
-
A Response to the Reply Presented in 'A Fair Comparison of Sliding-Mode and Immersion-and-Invariance Observers'
2026-10-14 19:00:13Luis Cervantes-P\'erez, V\'ictor Santib\'a\~nez, Jes\'us Sandoval, Romeo Ortega, Jos\'e Guadalupe RomeroAbstract
In response to the reply presented in [Muñoz-Vázquez and Sánchez-Torres(2026)], this technical report extends the experimental evaluation of position-feedback velocity observers and adaptive tracking controllers for a pendular system with nonlinear friction reported in [Cervantes-Pérez et al.(2026)]. The immersion and invariance (I&I) adaptive control scheme proposed in [Romero et al.(2025)], whose gains are tuned according to the guidelines presented in [Ortega et al.(2025)], is compared with a control scheme employing the adaptive modi?ed super-twisting observer of [Dávila et al.(2006)], whose observer gains are selected according to the guidelines proposed in [Muñoz-Vázquez and Sánchez-Torres(2026)]. Although these "tuning guidelines" attenuate chattering in certain scenarios, the experimental results reported here show that they do not eliminate it in general.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20815
PDF
-
Robotic-supported Data Loss Detection in Android Applications
2026-10-14 18:55:22Davi Freitas, Breno Miranda, Juliano IyodaAbstract
Smartphones have become integral to modern life due to their diverse applications. However, the development of applications for these devices faces significant challenges, primarily due to two factors: (i) the diverse hardware and operating system versions that require testing across multiple configurations; and (ii) the imperative activity of testing the smartphone in a non-invasive way (similar to an end-user interaction), which is expensive, tedious and error-prone as it is usually carried out manually. In this context, robotic automation has emerged as an effective solution for addressing the diversity of smartphone systems and versions, and in performing some testing tasks non-invasively. In addition, automated robots facilitate quick, accurate, and repetitive testing, thus enabling developers to validate their applications across various configurations effectively. This results in a less invasive verification and in a significant reduction in time spent on manual testing, thus accelerating the development cycle. Our work proposes R-DLD (Robotic-supported Data Loss Detection), a robot-assisted infrastructure for data loss detection in Android applications, offeringless invasive and more realistic tests by interacting directly with smartphone sensors. The robot is constructed using cost-effective materials, facilitating its adoption in testing environments. In our empirical evaluation R-DLD successfully identified 341 data loss issues in 77 randomly selected apps from an Android store. All reported bugs received responses from the developer, with 89.55% confirming the data loss problems, while 35.82% have being subsequently fixed.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20807
PDF
-
Navigation by Skylight Polarization via Rayleigh Model Optimization on a Road Vehicle
2026-10-14 18:41:52Ben Potter, Eslam Mounier, Aboelmagd Noureldin, Yahia Antar, Muhammad AlamAbstract
Reliable absolute heading estimation is critical for road-vehicle navigation, particularly when magnetic, inertial, or GNSS-based references are degraded. This paper presents a skylight polarization navigation method that estimates vehicle heading by globally optimizing a Rayleigh sky model against measurements from a division-of-focal-plane polarimetric camera. The proposed framework combines a pinhole camera model, a single-scattering Rayleigh polarization model, and a solar position algorithm to synthesize the expected full image angle of polarization distribution for candidate vehicle states. A degree of polarization weighted root mean square error objective function compares measured and simulated polarization patterns, allowing the estimator to use all available sky information while attenuating low confidence pixels caused by clouds, buildings, foliage, and other depolarizing occlusions. Experimental evaluation is performed using three urban road vehicle trajectories collected with a roof mounted polarimetric camera and a high precision dual-antenna GNSS/INS reference system. Results show sub-degree RMS yaw error across all trajectories, ranging from $0.718^{\circ}$ to $0.889^{\circ}$. Compared with representative feature-based and model-based polarization navigation methods, the proposed approach reduces RMS heading error by up to 87% and demonstrates improved robustness to partial sky occlusion.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20797
PDF
-
Multi-Dimensional Featurizers Yield Fine-Grained Steering and Data Shaping in Robot Foundation Models
2026-10-14 18:15:07Aiden Swann, Mozes Jacobs, Mathilde Papillon, Siddharth Boppana, David Chanin, Dron Hazra, Usha Bhalla, Curt Tigges, Mac Schwager, Owen Lewis, Jack Merullo, Ekdeep Singh Lubana, Atticus Geiger, Thomas Fel, Matthew KowalAbstract
Can better feature discovery improve control over robot behavior through internal interventions and training data? Recent work in vision and language models reveals multidimensional features, motivating block-sparse featurizers (BSFs), which represent each feature in a low-dimensional subspace. We investigate whether recovering this structure provides an interpretable interface for steering vision-language-action models and shaping the data from which they learn. We show that BSFs recover several multi-dimensional task-relevant features underlying the model's computation (e.g., perception, language, proprioceptive state, episode phase, and control variables). We causally validate these features through fine-grained steering: targeted changes in visual perception, semantic representation, and spatial localization produce predictable changes in downstream action prediction. Finally, we use feature-based data attribution to isolate where a specific behavior (failure recovery) arises in the training dataset, identifying fewer than $1.4\%$ of training tokens whose masking is sufficient to remove the targeted behavior. Overall, our results show how matching featurizers to representation geometry can provide more effective tools for understanding and changing robot behavior.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20767
PDF
-
Causal Analysis of Robot Foundation Models Enables Efficiency Gains
2026-10-14 18:06:47Aiden Swann, Mathilde Papillon, Mozes Jacobs, Siddharth Boppana, Tal Haklay, Eric Bigelow, Andrew Lee, Conor Watts, Thomas Icard, Mac Schwager, Owen Lewis, Jack Merullo, Ekdeep Singh Lubana, Atticus Geiger, Thomas Fel, Matthew KowalAbstract
Vision-language-action (VLA) models are a promising approach to general purpose robot manipulation. While the internal computation of vision-language models, which compose the backbone of VLAs, has been studied extensively, less is known about how their perceptual and semantic representations are transformed into action in VLA models. We study this question mechanistically in three frontier VLA models ($\pi_{0.5}$, MolmoAct2, and MolmoBot) by analyzing the causal pathways through which the input image and the instruction shape actions. Across the three models, activation patching shows that causally relevant information influences the action expert (AE) through a narrow band of mid-to-late cross-attention layers, which we term the action-conditioning interface. The content of this information changes with token and layer within the model. Early-to-mid layer representations of the target noun token determine which object is selected, whereas mid-to-late layers carry the spatial information in text tokens that redirects the movement when patched. Where spatial information is stored in prompt tokens various based on the architecture. In MolmoAct2 the model forms task-conditioned representations at the text positions that follow the instruction, whereas $\pi_{0.5}$ additionally stores this information at image token positions. We show that these findings can be translated directly into improving model efficiency. We find that restricting MolmoBot's action expert conditioning to only 3 out of 36 layers reduces inference FLOPs by up to $33\%$ while maintaining comparable task success with the default model across 3,000 evaluation episodes ($46.7\%$ vs. $46.9\%$), and the same principle carries over to real-robot deployment of $\pi_{0.5}$.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20750
PDF
-
SafeDriveVLA: Navigation-Conditioned World Model Dreaming for Conflict-Aware End-to-End Autonomous Driving
2026-10-14 17:59:56Shaoyuan Xie, Zihan Zhang, Jingxuan Wang, Jiashu Qu, Xiaoqing Liang, Lingdong Kong, Junchi Lu, Henrik I. Christensen, Qi Alfred ChenAbstract
Vision-Language-Action (VLA) models are gaining attention in autonomous driving, inheriting commonsense priors from large language models (LLMs) and widening the navigation interface from a fixed command set to free-form natural-language instructions. However, this open-ended interface exposes a new vulnerability surface: an inattentive driver may issue instructions that are unsafe given the current scene, and a malicious user may issue dangerous ones on purpose. We present the first benchmark suite that evaluates navigation following and conflict awareness together, along with adversarial robustness. Existing VLAs fall short on both: SimLingo completes no language-instructed lane change in closed loop, and all models degrade sharply under conflicting signals. We propose SafeDriveVLA, the first driving VLA that (1) explicitly predicts a three-level navigation-compliance mode to decouple conflict reasoning from action generation, and (2) uses navigation-conditioned world model dreaming to inform this prediction. Unlike prior world models that roll out expert or planned actions, ours dreams of strictly following the navigation signal, showing when following is safe. SafeDriveVLA reaches 88.16 Driving Score (DS) and 68.64% Success Rate (SR) on Bench2Drive, lifts closed-loop language following by 49.3% and reduces collisions under unsafe instructions from 60 to 38 compared to the best SimLingo variant. Video demonstrations are available on our project page.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20609
PDF
-
Hierarchical Residual Policy Learning for Real-World Mobile Manipulation with Sparse Human Guidance
2026-10-14 17:59:52Zhefei Gong, Hefeifei Jiang, Zehao Wang, Jiachen LiAbstract
Mobile Manipulation (MoMa) is a cornerstone of autonomous robotic systems, yet real-world fine-tuning remains a formidable challenge because of high-dimensional action spaces and intricate coupling between heterogeneous modules. In this paper, we propose HiRe-MoMa (Hierarchical Residual Mobile Manipulation), a systematic framework for stable and sample-efficient real-world fine-tuning of complex MoMa systems. At its core, HiRe-MoMa adopts a Hierarchical Residual Architecture that fine-tunes a frozen base policy. A Policy-Agnostic Residual learns additive corrections atop the base policy, while Hierarchical Decoupling splits the residual into mobile-base and manipulator-arm heads with unidirectional conditioning, mitigating gradient interference and aligning corrections with the platform's physical hierarchy. To improve sample efficiency in data-expensive real-world settings, we propose Expert-Guided Value Alignment, which leverages sparse human interventions with under 20% training coverage to reshape the critic's value landscape, effectively guiding autonomous exploration through expert priors. Extensive real-world experiments on the TIAGo++ platform demonstrate that HiRe-MoMa consistently enhances task performance with only around 30 minutes of online interaction, regardless of the base policy architecture. To our knowledge, this is among the first frameworks to enable efficient on-robot fine-tuning for mobile manipulation in the real world, providing a practical paradigm for deploying complex robotic systems in dynamic, human-centric environments. Further details can be found on our project website: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.20607
PDF
-
Modeling and Understanding Neural Weights of Humanoid Policies with Diffusion
2026-10-14 17:59:52Huixuan Cheng, Bike Zhang, Shankar Sastry, Koushil SreenathAbstract
Recent advances in robot learning have driven rapid progress in humanoid control, enabling increasingly agile behaviors in the real world. However, humanoid control networks are typically obtained through conventional training procedures, while comparatively little attention has been given to directly modeling the distribution of their learned weights and generating functional networks in weight space. In this work, we investigate whether high-performing humanoid control networks can be generatively modeled directly through their weights. We adopt a latent diffusion framework that couples a linear autoencoder with a Diffusion Transformer. The autoencoder compresses actor network parameters into a compact latent space, and the Diffusion Transformer models the distribution of these latents. Trained on networks collected from reinforcement learning for the Unitree G1 robot, our approach generates deployable networks that perform various motions in the real world, including walking, dancing, and spin kick. Beyond generation, we further study the learned weight space to better understand the structure captured by these humanoid control networks. We identify a structural principle in the first-layer weights that consistently reflects the robot's kinematic prior. Notably, this kinematic prior emerges under both Reinforcement Learning (RL) and Imitation Learning (IL) training, suggesting that it is not specific to a particular optimization process but may instead reflect common knowledge associated with humanoid embodiment. Together, these results demonstrate the feasibility of generative modeling in humanoid network weight space, while providing initial insights into the information encoded by their learned weights. Additional results are available on our project website: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.20606
PDF
-
CoWear: Towards Collaborative Wearable Inertial Localization with Multiple Smart Devices
2026-10-14 17:59:19Zhuoyuan She, Zhanpeng Zhang, Yapeng Chen, Jiale Wang, Xin Xie, Ming XiaAbstract
Consumer smart devices observe the same human motion from different body locations, yet existing inertial-localization benchmarks rarely provide synchronized heterogeneous wearables with device-specific motion ground truth. We present CoWear, a dataset and reference framework for collaborative inertial localization using a smartphone, smartwatch, and smart glasses. The dataset contains over 30 participants, over 300 walking sessions, and more than 30 hours and 100 km of aggregate device trajectories, with each device individually tracked by motion capture. To enable collaboration across distinct body motions, we train role-specific estimators to predict the displacement of a common reference device over synchronized temporal windows. Their predictions are transformed to the world frame using gyroscope integration and fused according to learned uncertainty. Experiments using phone, glasses, and watch as reference targets show that multi-device fusion consistently improves both displacement and trajectory rollout accuracy over individual-device estimation. CoWear provides a dataset and reproducible baseline for studying collaborative inertial localization across heterogeneous consumer wearables.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20596
PDF
-
PingpongDuo: Agile Humanoid Table Tennis Doubles with Safe Team Coordination
2026-10-14 17:56:27Haoran Jiang, Yichao Zhong, Kai Zhang, Cheng Liu, Yixuan Pan, Zhenjie Yang, Jingbo Wang, Tianyu Li, Li ChenAbstract
Unlike singles, humanoid table tennis doubles requires teammates to strike in strict alternation while sharing a confined workspace. Rapid repositioning can compromise striking accuracy, while uncoordinated teammate movements introduce collision risks. We present PingpongDuo, a hierarchical framework for agile humanoid doubles with safe team coordination. At the team level, a planner jointly selects positioning targets and uses learned risk estimates to filter risky proposals, preferentially preserving the current striker's target. At the individual level, separate footwork and striking skills combine agile movement with precise racket control. The skills are guided by human motion references, including footwork collected from human doubles play, and trained from states produced by one another to support rapid transitions. A racket-arm residual further refines strikes after movement using return feedback from a simulator calibrated with real ball-flight and contact measurements. In simulation, PingpongDuo improves the ball-return success rate by 13.2% over the state-of-the-art baseline, while achieving approximately 2 cm positioning error during clearance. In real-world experiments, a robot completes a 2.15 m clearance-and-recovery cycle in 2.4 s with a peak speed of 2.23 m/s, while two robots sustain more than 10 consecutive strikes in strict alternation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20579
PDF
