Tracking
-
LIN-SLAM: Lightweight LiDAR--Inertial Neural SLAM for Real-Time Onboard Navigation
2026-10-15 03:58:47Shiqi Che, Yijie Liu, Shuo Wang, Wenxin LiuAbstract
Geometric light detection and ranging (LiDAR)--inertial simultaneous localization and mapping (SLAM) provides efficient state estimation but lacks the continuous map representation and global refinement capabilities of neural implicit SLAM, while neural implicit methods remain computationally expensive. We propose Lightweight LiDAR--Inertial Neural SLAM (LIN-SLAM), a hybrid method that couples high-rate geometric LiDAR--inertial estimation with neural implicit tracking, continual mapping, and global refinement for accurate real-time onboard SLAM. Experiments on twelve representative sequences from three datasets spanning 32-, 64-, and 128-channel LiDAR configurations show that LIN-SLAM achieves the lowest overall mean absolute trajectory error (ATE) among the evaluated state-of-the-art geometric and neural implicit methods, while substantially reducing runtime compared with existing neural implicit SLAM methods. On a Unitree Go2 equipped with an NVIDIA Jetson Orin NX and a 16-channel LiDAR, LIN-SLAM sustains real-time localization and neural mapping over a 1.47-km indoor trajectory through challenging repetitive corridor environments, with an endpoint closure error of only 0.141~m. To the best of our knowledge, LIN-SLAM is the first LiDAR--inertial SLAM system with a neural implicit backend to achieve real-time online operation on a mobile robotic platform while maintaining state-of-the-art localization accuracy. The code will be released upon acceptance.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21199
PDF
-
Learning to Read Out: Unembedding Dynamics in Language Model Pretraining
2026-10-14 23:45:26Matteo He, William F. Shen, Alex Iacob, Andrej Jovanovic, Xinchi Qiu, Nicholas D. LaneAbstract
When does a language model acquire a capability? Developmental studies usually answer this by tracking when models start producing the correct token. But that prediction passes through the unembedding matrix, or readout, which is itself still being learned during pretraining. We show that a model's hidden states can encode task information before its own readout expresses it, so timelines read from outputs conflate what the model encodes with what its readout expresses. To track the readout directly, we introduce parameter-trajectory crosscoding, which fits one sparse dictionary to every token's readout row at every checkpoint. Unlike crosscoders on activations, it needs only checkpoint weights. We use it to locate a narrow early window, 0.4-1.1% of the way through Pythia's pretraining, in which the readout reorganizes and WordNet word categories become decodable from its rows. By then, linear probes on the hidden states already decode task information that the model's own outputs do not yet show. To test whether such gaps depend on how fast the readout learns, we pretrain small models from scratch that differ only in the readout's learning rate. We find that raising it makes the readout develop earlier and the gap close sooner, with little effect on final loss. Together, these results imply that early in training, where many developmental transitions are dated, a behavioral date can reflect when the readout learns to express task information and not when the model learns it.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21025
PDF
-
Audio-Visual Dog Identification and Tracking in Real-World Videos
2026-10-14 23:15:47Aryahvishwa Babu, Kingsley Jin, Lillian Wang, Tuan M. Dang, Theron S. Wang, Jeorge Joshi, Annie Cao, Kenny Q. ZhuAbstract
Identifying individual dogs from barks in real-world videos remains challenging and largely unexplored. Solving this problem would enable long-term behavioral analysis, veterinary monitoring, and animal welfare monitoring by attributing vocalizations and behaviors to the correct individual. Real-world videos are challenging because multiple dogs may bark simultaneously, become occluded, or move in and out of view. Prior studies show that canine vocalizations and visual appearance contain discriminative identity information, but these modalities have largely been studied independently. We present a multimodal dog-fingerprinting framework combining visual identification, multiple-object tracking, and canine vocal fingerprinting to associate bark events with individual dogs while maintaining persistent profiles. The framework synchronizes bark events with tracked dogs and updates profiles using visual appearance and vocal characteristics, enabling identification despite occlusion, overlapping vocalizations, and off-screen barking. We also introduce a benchmark of 46 real-world videos containing 213 manually annotated bark events. Our framework correctly localizes the active visible dog in 61.83% of visible events at IoU $\geq 0.30$ and achieves a 91.33% F1 score for visible versus off-screen barking detection.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21011
PDF
-
SOMA: Stack-of-Objects Manipulation using a Quadruped Robot
2026-10-14 21:43:14Stergios E. Bachoumas, Panagiotis ArtemiadisAbstract
Executing heavy-duty physical manipulation in unpredictable environments remains a major challenge for quadrupedal robots lacking dedicated manipulators. This paper presents SOMA, a hierarchical reinforcement learning framework for whole-body non-prehensile manipulation of multi-object stacks using a quadruped robot. Unlike traditional methods restricted to two-dimensional planar pushing, SOMA integrates explicit robot base-height control, unlocking full three-dimensional pushing strategies. This capability enables the quadruped to manipulate complex payload stacks as a unified system while preventing relative sliding or tipping of upper layers. The architecture factorizes control into a high-level manipulation policy using a Simplified Structured State Space Sequence (S5) encoder to reason over long-horizon temporal history and predict bounded target tracking commands via Beta distributions, and a low-level locomotion policy that dynamically adapts leg stance configurations. In extensive simulation benchmarks, SOMA achieves a $90.3\%$ success rate for single-object reposing and up to $90.1\%$ for dynamic two-box stacks under stringent error margins ($0.05\text{ m}$ position error, $1^\circ$ orientation error). Finally, we validate zero-shot sim-to-real transfer on a Unitree Go1 quadruped robot across diverse payload masses and geometries, demonstrating active base-height adjustments to maintain traction and balance during heavy pushing tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20968
PDF
-
Line-Augmented cuVSLAM: Robust Visual Odometry in Low-Texture Environments
2026-10-14 21:29:40Dara Molloy, Terry Wu, Wonju Lee, Abhilash Nand Kumar, David Adley, Conor Ferguson, Hesam RabetiAbstract
Autonomous mobile robots in warehouses and production facilities operate in precisely the environments that defeat point-feature visual odometry: featureless aisles, uniform walls, repetitive racking and specular floors. Such environments are, however, rich in straight-edge structure: rack uprights, door frames, wall junctions and cabinet outlines present high-contrast linear edges stable across wide viewpoint changes. A line-feature extension to cuVSLAM, a CUDA-accelerated visual-SLAM system, is presented that recovers this signal. Lines are parameterised as Plücker coordinates for geometric transport and as the minimal 4-DOF orthonormal representation of Bartoli and Sturm for optimisation; a Cauchy-robust point-to-line residual with analytic Jacobians is folded directly into cuVSLAM's per-frame Gauss-Newton pose solve, and the same line state is jointly refined in the Schur-complement sliding-window bundle adjustment. An adaptive information weight causes lines to assume more of the estimation burden exactly as point features become scarce, and the extension adds residual blocks to existing solvers rather than introducing a second estimator, reducing exactly to the unmodified point pipeline when disabled. Evaluated in RGB-D mode under SE(3) Umeyama alignment with no scale correction, line features reduce mean absolute trajectory error by 38.5% over the 22 sequences of the TUM RGB-D Freiburg3 collection and by 30.1% over the 8 Replica room and office sequences, where median translation error falls by 38.9% and median rotation error by 66.4%, with zero tracking failures in any configuration tested.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20958
PDF
-
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
-
EgoJEPA: Beyond Retargeting for Dexterous Manipulation from Egocentric Videos
2026-10-14 20:34:18Meng Cao, Can Zhao, Jinjie Wei, Haonan Zhao, Yulong Zhang, Duo Han, Xiaofan Li, Ziwu Song, Rongtao Xu, Ruyi Gan, Hao Wang, Qian Wang, Daolin Ma, Ian Reid, Xiaodan LiangAbstract
Egocentric human videos offer a scalable alternative to costly robot demonstra- tions, yet transferring their manipulation priors to robot control remains chal- lenging. The commonly adopted retargeting-based approaches convert human wrist and finger poses into embodiment-specific action commands through hand- crafted geometric mappings. However, such mappings require meticulous recal- ibration across different embodiments and risk propagating hand-tracking errors into downstream robot control pipelines. To this end, we propose EgoJEPA, a three-stage framework that learns embodiment-agnostic representations from ego- centric human videos without rule-based human-to-robot retargeting: 1) Human- action pre-training learns effect-aware latent actions through JEPA-style visual prediction conditioned on hand-motion differences; 2) Latent-action-based world modeling jointly predicts future visual dynamics and latent actions, which decou- ples human prior pre-training from robot-specific control parameterizations; 3) Embodiment-specific tuning adapts the pretrained model to diverse robots through lightweight action adapters. Experiments on five real-world manipulation tasks across three robot embodiments demonstrate the effectiveness and efficiency of EgoJEPA. It achieves a 74% average success rate under the out-of-domain evalu- ation, compared with 65% for the retargeting baseline, while reducing cumulative cross-embodiment wall-clock cost by 47.2%, from 743.2 to 392.7 hours.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20904
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
-
A Self-Improving Agent that Grows its Own DSL: Oracle-Free Operator Induction for Exact Question Answering
2026-10-14 18:55:34Yun-Shiuan Chuang, Yirou Ge, Yixi Li, Yiming Bian, Zijie Pan, Jenna L. Ballard, Uma Kona, Linsey Pang, Prakhar MehrotraAbstract
A self-improving agent has to decide which new skills to keep, and in practice it keeps whatever earns a high reward, convinces a judge model, or compresses its library, even when the skill is wrong. That is fine until the answers have to be exactly right: over a table of transactions, a total is either right or wrong. We ask a harder question: can an agent grow what it can compute with no reward, no judge, and no answer key, and still be exactly right? A single frozen model runs two nested loops over a small, exact domain-specific language (DSL). The inner loop answers new questions only when two independently written expressions agree on every record. The outer loop discovers its own missing capability and authors an operator for it, admitted only when an independent second implementation agrees and the result obeys a conservation law, all without ground truth. The inner loop roughly triples the answerable-question set, and the outer loop self-extends on disjoint starting sets, inventing operators outside the starting closure; a no-induction control answers none of the new questions. The admission rule is empirically sound: it rejects 138 of 138 buggy operator variants under an independent reference, even one written by a different model family, where the admit-if-it-runs, self-consistency, and compression signals the field relies on admit most of them. Unmodified, the same mechanism self-extends on two further domains with unrelated schemas, business-ledger and clinical-encounter question answering, growing their answerable sets more than tenfold and nearly twentyfold. The loop transfers across model families too: run with further proposers, the gate stays sound and independent families self-extend comparably, with only the induction yield tracking each proposer's DSL fluency.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20809
PDF
-
KinoGen: Customizable Humanoid Loco-Manipulation References via Kinematically Grounded Video Generation
2026-10-14 17:43:32Qi Wu, Lulu Zhao, Sanghyun Hahn, Rishi Yennu, Emmy Yang, Dingqi Zhang, Tao Pang, Jiuguang Wang, Kuan FangAbstract
We present KinoGen, a framework that synthesizes customizable humanoid loco-manipulation references through kinematically grounded video generation. KinoGen conditions a pretrained video generator on calibrated renders of the target robot and object in a simulated task instance and recovers the reference by fitting the same models to the generated two-view video, so that the reference lies in the robot configuration space by construction without a human body proxy or retargeting. Body, hand, and object priors initialize the reconstruction, and direct optimization against cross-view evidence refines it. Since an edited keyframe is simply another rendered state, a user can prescribe a goal object pose, regenerate the video around the edited keyframe, and obtain a reference that satisfies the pose exactly. Across eight loco-manipulation tasks, KinoGen yields lower penetration and foot skating than video-based baselines and preserves over 90% of annotated contacts, and its customized references satisfy every prescribed target with substantially less penetration than direct interpolation. Tracking policies trained on the synthesized references are deployed on a Unitree G1 humanoid with dexterous hands. Project webpage: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20552
PDF
-
VIGOR-MPC: Vision-Guided Objective Regulation MPC
2026-10-14 15:15:32Jelena Trisovic, Rahel Rickenbach, Marek Landert, Panagiotis Minos, Melanie N. ZeilingerAbstract
Controlling an agent in an environment solely perceived through onboard vision is challenging: perception yields noisy, variable-length, and partially occluded context, while onboard compute is shared between perception and control, limiting the planning horizon executable in real time. We propose VIGOR-MPC, a modular student-teacher framework, agnostic to the perception pipeline, which addresses reference tracking across navigation tasks by distilling a privileged, field-of-view-aware long-horizon MPC into a computationally lightweight short-horizon MPC whose cost parameters are determined online from vision. The teacher operates in simulation with full state knowledge and a multi-trajectory formulation that guarantees the agent can stay within its field of view. The student observes only the noisy, occluded context produced by a perception module and learns, via a multi-level recurrent mapping, to infer cost parameters that aim to recover the teacher's behavior despite missing information. We evaluate VIGOR-MPC on vision-based autonomous racing in simulation and on hardware. Using only onboard perception of the track, VIGOR-MPC generalizes to tracks unseen during training and approaches the lap times of the privileged long-horizon teacher while reducing per-step computation by over 90%.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20333
PDF
-
VICON: Visual-Inertial-Contact based Hand-Object Tracking for Manipulation Datasets
2026-10-14 15:07:17Youbeen Jeon, Uiseong Shin, Hwanchul La, Jaeseong Kang, Hyelim Choi, Yongseok LeeAbstract
Learning dexterous manipulation benefits from human demonstration datasets that capture diverse and natural hand-object interactions. In particular, contact points and forces provide supervision on where and how strongly to interact, which cannot be fully captured by motion trajectories alone. However, methods for jointly capturing hand and object motion, contact points, and forces remain limited. Moreover, severe occlusion from hand-object interaction challenges accurate tracking of both hands and objects. To address these limitations, we present a Visual-Inertial-CONtact based hand-object tracking (VICON) framework. It holistically captures both hand and object motion along with contact information during manipulation, even under severe occlusion. First, we adopt a visual-inertial glove and an RGB-D camera for accurate hand tracking, and redesign the glove to incorporate contact sensing. Specifically, force-sensitive resistors (FSRs) are placed on the glove based on human grasp frequency to synchronously record contact states and calibrated normal forces. Second, without requiring pre-existing CAD models, we estimate object poses using RGB-D images and a mesh reconstructed from a monocular video. We propose factor-graph-based object trajectory estimation that fuses object-pose estimates weighted by visibility under hand-object occlusion, FSR measurements, and a hand-motion prior. Across 40 motion-capture sessions with five objects, VICON achieves a 2.5% failed-frame rate compared with 50.9-64.6% for the baselines, with median errors of 3.9 mm and 3.0 degrees under occlusion. Using VICON, we construct a dataset containing synchronized hand-object motion, contact points, and normal forces, and will publicly release an expanded dataset covering 10 object categories at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.05180
PDF
-
SAM3RL: Memory Control via Reinforcement Learning for Visual Object Tracking
2026-10-14 10:17:47Tom\'a\v{s} \v{C}\'i\v{z}ek, Matej Straka, Illia Volkov, Mat\v{e}j Kripner, Ervin Maci\'c, Jiri Matas, Klara Janouskova, Martin SchmidAbstract
Segment Anything Model 3 (SAM 3) is a foundation model for image and video segmentation that sets the state of the art in visual object tracking. Its tracker, inherited from SAM 2, stores information from past frames in a memory bank, managed by a simple First-In-First-Out rule, allowing temporal consistency in complex videos. Several recent methods improve SAM 2 with hand-crafted memory update rules, each targeting a specific failure mode, such as distractors, occlusions, or object motion. However, their gains transfer only partially to the stronger SAM 3 backbone. We instead present a more general, data-driven approach that frames memory control as a sequential decision-making task. SAM3RL is an extension of the SAM 3 tracker with a lightweight memory controller, trained by reinforcement learning, that decides which frames enter the memory bank in order to maximize tracking performance. SAM3RL sets a new state of the art on 10 of 12 tracking and video object segmentation benchmarks, outperforming all hand-crafted rules without any runtime overhead. The same approach applied to SAM 2 gives SAM2RL, which outperforms hand-crafted rules on 9 of the 12 benchmarks, showing the generality of our method across model generations.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19931
PDF
-
OmniPoser: Flexible Human Motion Recovery in the Wild with Masked Flow Matching
2026-10-14 09:22:48Minghao Liu, Tutian TangAbstract
Recovering 3D human motion from sparse wearable sensors is challenging due to the inherent noise, occlusion, and instability of real-world tracking signals. Existing approaches are restricted to fixed sensor configurations and, when built on diffusion models, are computationally prohibitive for real-time deployment. We propose OmniPoser, a universal framework that recovers full-body SMPL motion from a flexible combination of heterogeneous inputs, such as 3D keypoints, sparse IMU rotations, head-mounted 6-DoF poses, or any subset thereof, within a single model. OmniPoser introduces a cross-modal masking mechanism paired with a Masked Conditioning Encoder, enabling one architecture to incorporate diverse sensor configurations through a masked design. A decoupled dual-stream generative backbone generates complete motion via Conditional Flow Matching, requiring only a single ODE integration step at inference. Across three settings and seven benchmarks, including in-the-wild Nymeria and Ego-Exo4D datasets, OmniPoser performs on par with state-of-the-art methods while running at over 700 FPS. The project page is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19857
PDF
-
StateCraft: Augmenting Video World Models with Abstract-State Reasoning
2026-10-14 08:39:41Lorenzo Venturoli, Nedko Savov, Xi Wang, Marc Pollefeys, Luc Van GoolAbstract
Video world models aim to simulate complex environments with realistic appearance and dynamics. Maintaining consistency over long interactions requires tracking past actions and understanding how those actions affect the environment. Video world models can only generate partial observations of the entire world at a time. Remembering past observations alone may not be sufficient in every scenario, as they may no longer reflect the world after a sequence of actions. We introduce a paradigm that decouples a persistent, updatable abstract state from the visual state. The abstract state keeps track of the entities' changes as the world evolves, and is used to condition the visual state, which represents the current view. We propose StateCraft, a novel architecture that pairs a language model with a video diffusion model to evolve the dynamic world. We evaluate our approach on generative interfaces, which pose a substantial challenge because a single action may change parts of the state that are not currently visible. To support training and evaluation, we develop a data collection pipeline that produces informative, densely annotated trajectories at scale without human or agent supervision, together with a benchmark measuring generation quality, memory, and controllability. On this benchmark, our approach improves surpasses the state-of-the-art baselines. We demonstrate that StateCraft maintains high self-consistency and strong generation quality over long trajectories. Because the abstract state is explicit, it can be edited directly, and generation follows edits to states never observed in the data. Finally, a proof-of-concept 3D experiment, in which actions change the illumination of an unobserved room, shows that the paradigm can also be applied to spatial environments. Project page: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19795
PDF
-
4DVLT: Dynamic Scene Understanding with Worldline-Centered Vision-Language Tracking
2026-10-14 08:38:19Boxue Yang, Chaoyue Li, Shengyao Zhou, Rui Qian, Haoyang Wu, Shaoqiu Zhang, Linfeng ZhangAbstract
Language-guided dynamic scene understanding requires identifying one physical entity across time, metric 3D space, and multiple viewpoints, a setting not captured by current multimodal reasoning or tracking paradigms. We introduce 4DVLT, an offline calibrated multi-view task that unifies grounding with metric 3D and synchronized 2D tracking through a worldline binding identity, motion, visibility, and observations. We construct Instruct-4D, with 129.4K QA pairs, 64.7K targets, 851 scenes, and 9 reasoning types, and propose 4DTrack for query-conditioned inference over a 4D state graph. 4DTrack reaches 55.18 WQS, exceeding the strongest adapted VLT baseline by 33.01 points while improving grounding and trajectory quality. The project page is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2606.22631
PDF
-
Eye, Robot: Learning Expressive Gaze Dynamics via a VLM-Guided Transformer-VAE
2026-10-14 06:04:04Yuhang Hu, Junlin Lyu, Yuan Fang, Xiaoying Shen, Lechen Zhang, Jiong Lin, Judah Goldfeder, Steven Tian, Hod LipsonAbstract
Gaze coordinates attention in human interaction through coupled eye, head, and eyelid motion. A humanoid robot must choose where to look while generating a suitable movement toward that target; fixed tracking rules alone do not model the temporal structure of human gaze. We separate these tasks with an asynchronous vision-language model that selects a scene referent, a reactive perception module that maintains fixation, and a Realistic Gaze Transformer (RGT) that generates target-conditioned motion. RGT is a Transformer-VAE trained on markerless human recordings retargeted to the robot's 11-DoF joint space: self-supervised pretraining encodes recent full-head history, and autoregressive fine-tuning exposes the model to its own predictions during rollout. At inference, a four-dimensional binocular-eye trajectory conditions coordinated neck and eye motion; an auxiliary blink predictor triggers eyelid templates during playback. On a two-second benchmark in which all controllers receive the same ground-truth target, RGT-Base obtains the lowest reported overall seven-joint MSE, and physical demonstrations show the integrated targeting and control pipeline. The evidence establishes robot-space kinematic fidelity and real-time RGT inference; perceived naturalness and open-vocabulary target-selection accuracy remain questions for controlled evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19635
PDF
-
E2DRL: End-to-End Differentiable Reinforcement Learning for 3D Obstacle Avoidance in Quadruped Robots
2026-10-14 05:54:25Cheng Fan, Bingyang Zhou, Gang Yang, Zixuan Zhuang, Aoqian Zhang, Pengzhi Yang, Xin Liu, Chunzheng Wang, Yan Rui Tan, Fan ShiAbstract
Differentiable reinforcement learning shows strong promise for robot policy learning, but its application to legged locomotion has remained limited to blind walking or simulated 2D tasks. Extending it to end-to-end visual obstacle avoidance is challenging because hard collision constraints and early termination upon contact corrupt first-order gradients, trapping optimizers in local minima. We present E2DRL, which addresses this with a soft differentiable obstacle-interaction formulation: penetration penalties across multiple body keypoints with velocity-conditioned stop-gradient shaping to provide the first-order training signals for 3D obstacle avoidance. To realize a deployable perception-control system, a privileged teacher trained via Soft Analytic Policy Optimization (SAPO) in a differentiable simulator is distilled into a recurrent depth-based student via DAgger, then blended with a base locomotion policy using a terrain-aware gating module for deployment. In simulation, E2DRL achieves higher sample efficiency than PPO and demonstrates superior velocity-tracking performance and 3D obstacle-avoidance capability compared with both PPO and Duality-based DCBF NMPC. We present the first sim-to-real validation of end-to-end differentiable RL for 3D obstacle avoidance on a Unitree Go2 in static and dynamic environments.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19627
PDF
-
Spacecraft Pose Tracking via Kinematic Prediction and Selective Event Correction
2026-10-14 02:46:18Yonglong Zhang, Guanning Yao, Shuo Zhang, Yifan Yang, Yang Liu{\dag}, Zongwu XieAbstract
In initialized spacecraft tracking, a short-horizon motion prediction remains available as event support changes. Observation-Aligned Event Innovation (OA-EI) uses events to correct selected components of this prediction. A constant-body-twist model propagates the complete pose; the event encoder proposes rotational and normalized image-plane translation corrections, retaining propagated axial depth. Candidate magnitudes come from a bounded Scale Gate and a deterministic activity factor, with empty windows returning the prediction unchanged. Evaluation uses four FRESH physical-event trajectories, twenty rollout starts, and three training seeds. Each rollout starts from two reference poses and then uses self-estimates. At 7.7 seconds, rotation and translation errors fall from 41.63°/57.28 mm for prediction alone to 15.73°/22.41 mm for OA-EI, reductions of 62.2% and 60.9%. Failure rates fall from 20.0% to 1.67%. Matched ablations favor the rotation-bearing interface for overall pose accuracy; combining scaling with activity support gives the lowest errors at every tested event-retention level. On Jetson Orin Nano, the measured in-memory update takes 44.56 milliseconds at the median and 58.77 milliseconds at P95.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19465
PDF
