https://arxiv.org/api/7p0XQKj29+lXlri1dAXIzZ5fcHU 2026-09-16T17:45:02Z 20 116 0 http://arxiv.org/abs/2609.09821v1 2026-09-09T07:23:51Z

Physics-based character control is a long-standing challenge in computer graphics and robotics, requiring policies that satisfy complex dynamics while producing realistic motion. Recent Deep RL approaches, particularly imitation learning methods such as DeepMimic, have had broad impact beyond animation, influencing robotics by enabling agile and expressive behaviors. While these approaches achieve impressive results, they remain computationally inefficient to train in practice. Despite GPU-accelerated simulation, we find that end-to-end pipelines often underutilize hardware due to overheads outside the physics solver, caused by fragmented GPU kernels and CPU memory access in the critical path. We present InstantMimic, a system that addresses these inefficiencies by making the entire training loop GPU-native. Built on a GPU-native physics backend, our unified pipeline integrates simulation, environment computation, policy inference, and policy updates within a single execution flow. As a result, InstantMimic reduces training time for diverse physics-based skills to a few seconds and makes LLM-agent-driven hyperparameter search practical.

2026-09-09T07:23:51Z Accepted to SIGGRAPH Asia 2026 Conference Papers. 11 pages, 11 figures. Project page: https://scripter36.github.io/projects/instantmimic/ Ikjun Choi Geonho Leem Jungdam Won http://arxiv.org/abs/2609.06591v1 2026-09-06T13:16:48Z

Developing unified physics-based humanoid controllers that can navigate complex 3D scenes and manipulate objects remains a longstanding challenge. Existing approaches are often specialized for either locomotion or object-centric manipulation, or rely on task-specific reward engineering that does not scale well across diverse behaviors. We present CHIP, a unified, physics-grounded framework for learning reusable humanoid interaction skills from heterogeneous motion data. Central to our approach is a conditional interaction prior that models a context-dependent distribution over these skills within a shared discrete space. Our method is trained in three stages. We first learn physics-based motion-imitation policies that acquire grounded teacher behaviors from heterogeneous interaction data. We then distill these behaviors into a context-conditioned interaction prior that captures reusable motion structure across locomotion and manipulation. Finally, we initialize downstream task policies from the pretrained prior and adapt them through prior-regularized online RL post-training. Experiments on a diverse suite of humanoid interaction tasks show that our approach supports scene-aware locomotion, contact-rich object manipulation, and compositional behaviors such as environment-aware object transport and long-horizon skill sequencing, while producing smooth transitions and physically plausible motion.

2026-09-06T13:16:48Z Accepted at SIGGRAPH Asia 2026. Project page: https://jiann-li.github.io/chip-project/ Jianan Li Xiao Chen Tien-Tsin Wong http://arxiv.org/abs/2608.23258v1 2026-08-24T13:48:45Z

We propose HetSkills, a novel framework designed to progressively learn heterogeneous skills within a unified latent space for physics-based character control. The core idea is to treat this latent space as a shared executable interface, enabling seamless integration of skills learned from diverse data sources, supervision forms, and tasks. HetSkills begins by learning a tracking skill that establishes a strong foundation in motion control and creates a shared motion decoder, which can be reused across tasks without the need for retraining or separate controllers. To prevent the text-to-motion skill from exploiting shortcut pathways instead of learning language semantics, we introduce motion intuition distillation to ground text-to-motion generation in language semantics and a task-guidance module that dynamically adjusts actions based on high-level language instructions. This enables HetSkills to preserve natural motion while continuously expanding its skill repertoire, making it highly adaptable for long-horizon tasks. Experimental results demonstrate the effectiveness in motion tracking, text-to-motion generation, motion completion, and downstream task adaptation, achieving impressive success rates even under challenging conditions.

2026-08-24T13:48:45Z 23 pages, 18 figures Yue-Yi Zhang Ming Gong Linpu He Wei-Shi Zheng Zhilin Zhao http://arxiv.org/abs/2608.03528v1 2026-08-04T12:12:09Z

Replicating human behavior with physics simulation has been a long-expected goal in character animation. Existing efforts have achieved impressive performance in imitating a wide span of general motions. However, most existing efforts could still suffer from unnatural movements due to the lack of biomechanical and physiological priors. Given this, we project our sights to advances in behavioral energetics, which demonstrate how energy use shapes human movements. In contrast, current character controllers typically assume the character is equipped with infinite energy over time. Inspired by these, we propose to adopt fatigue as a proxy of the finite energy limit, inject it into general character animation, and thoroughly investigate how fatigue introduces new characteristics to physics-based character control. Leveraging the Three-Compartment Controller (3CC) model, we managed to obtain a policy for general motion imitation under different fatigue statuses. Furthermore, extensive analyses are conducted to demonstrate how fatigue could influence the naturalness, scalability, and robustness of character animation. Our code will be made public.

2026-08-04T12:12:09Z 14 pages, 13 figures Shengyuan Zhang Xinpeng Liu Muchun Niu Yulong Chen Lizhuang Ma Yue Gao Cewu Lu Yong-Lu Li http://arxiv.org/abs/2608.03227v3 2026-09-03T11:02:55Z

Motion priors improve reinforcement learning for physics-based humanoid tracking, but temporal priors require ordered motion clips, while pose priors provide limited guidance for policy-induced pose transitions. We present Pose Flow Matching for Humanoid Robots (PFM-HR), a reusable flow matching prior trained directly on large scale unordered pose data. PFM-HR introduces the Pose Geometry Score (PGS), which quantifies how joint coordinate changes during rollouts align with the local geometry of pose variation captured by the prior. Using PGS to modulate the tracking reward guides policy exploration toward structured pose changes while keeping the prior frozen across tracking tasks. Experiments demonstrate that PFM-HR improves both single motion and general motion tracking, especially for highly dynamic motions.

2026-08-04T06:58:54Z 7 pages Yukang Gao Yi Gu Yangchen Zhou Xingyu Chen Zhaorui Wang Fanghai Zhang Hanyang Cao Zhengyang Shen Ji Ma Runhan Zhang Lei Han Renjing Xu http://arxiv.org/abs/2606.29209v1 2026-06-28T05:20:37Z

We present AnyBody, a unified whole-body humanoid controller driven by an arbitrary subset of body keypoints chosen at deploy time. Prior physics-based trackers either rely on expensive full-body motion capture and error-prone trajectory retargeting, which bottleneck scalable data collection and policy learning, or decompose upper- and lower-body control into separate hierarchical representations, sacrificing the coordinated whole-body motions that loco-manipulation requires. We close this gap by learning a single latent motion representation that any keypoint subset can address. To achieve this, we first train a privileged teacher tracker on a large unstructured motion corpus and distill it online into a deterministic encoder-decoder student whose latent space is a unit sphere. We then train a transformer keypoint encoder that admits any subset of body keypoints through masked self-attention, aligning it to the privileged latent. Additionally, we treat the frozen decoder as a motor prior and specialize downstream tasks with a lightweight residual corrector in the latent space. We demonstrate the effectiveness of AnyBody by tracking large-scale human motions from arbitrary keypoint subsets, free-form control, flexibly teleoperating, and learning downstream behaviors including locomotion, in-air writing, and obstacle-reach.

2026-06-28T05:20:37Z Shuning Li Sikai Li Jiachen Li Mingyu Ding http://arxiv.org/abs/2606.29148v1 2026-06-28T02:05:11Z

Developing controllers capable of completing a wide range of tasks in a natural and life-like manner is a key challenge in enabling practical applications of physics-based character animation. In this work, we introduce Generative Pretrained Controllers (GPC), which leverage tokenization and next-token modeling to create general-purpose, reusable generative controllers from large-scale motion datasets. Our framework utilizes end-to-end reinforcement learning to jointly optimize a "motion vocabulary", modeled via Finite Scalar Quantization (FSQ), along with a corresponding control policy that can map the discrete codes to physics-based controls. After the "codebook" has been learned, the underlying structure of this large vocabulary is modeled by training a GPT-style autoregressive transformer, leading to a powerful generative controller that generates controls for a physically simulated character by performing next-token prediction. Once the generative controller has been trained, we propose a suite of adaptation techniques for finetuning the controller for new downstream tasks. Our proposed framework greatly simplifies the training process compared to previous tokenized methods, and achieves a 99.98% success rate in reproducing a vast corpus of motion clips. The generative controller exhibits a variety of natural emergent behaviors, such as responsive behaviors to perturbations and recovery behaviors after falling. This results in highly robust general purpose controllers for a variety of downstream applications.

2026-06-28T02:05:11Z SIGGRAPH 2026 Conference Proceedings Yi Shi Yifeng Jiang Chen Tessler Xue Bin Peng http://arxiv.org/abs/2606.25056v1 2026-06-23T18:12:22Z

Behavioral Foundation Models (BFMs) offer a promising path toward universal physics-based character control by organizing a rich repertoire of physically plausible behaviors into a latent space, guided by a large-scale motion dataset. While these models excel at time-invariant tasks, such as goal-reaching and state-based reward optimization, their latent space does not directly support time-varying objectives, such as tracking a motion sequence. For tracking, existing heuristics rely on moving-window-averaging that fails to capture the nuances of highly dynamic motions. In this work, we propose a novel Latent Sequence Optimization (LSO) to address these shortcomings. Our approach combines simulation rollouts with a policy gradient update to optimize over a sequence of latents, extending the capabilities of BFMs toward precise motion tracking without requiring reward engineering and tuning. To guide the optimization toward smooth, coherent latent trajectories, we model the latent sequence using temporally correlated noise. We validate our approach across dense tracking, sparse keyframing, and direct deployment onto a real humanoid robot.

2026-06-23T18:12:22Z Thomas Rupf Agon Serifi David Müller Sammy Christen Ruben Grandia Espen Knoop Moritz Bächer http://arxiv.org/abs/2606.15918v1 2026-06-14T16:46:18Z

Humanoid robots performing in-field manipulation tasks, such as robotic apple harvesting, face severe energy constraints that directly limit the number of reaching motions that can be executed per battery charge. This paper presents an end-to-end, energy-aware reinforcement learning framework for the 7-degree-of-freedom left arm of the Unitree~G1 humanoid robot, combining a physics-based, experimentally identified electrical power model with a Soft Actor-Critic (SAC) policy trained in a Pinocchio-based rigid-body dynamics simulator. The RL policy operates on an incremental joint-position action space and is trained with a Hybrid Constellation Reward that combines a four-point end-effector constellation distance with a torque-norm energy proxy; after % $5\times10^6$ training it reaches a $69.9\%$ success rate over $1\,000$ random targets in kinematic simulation, at a mean energy of \SI{98.16}{\joule} on successful episodes. Finally, on the physical Unitree~G1, the policy is validated over three independent 10-target batches, achieving a mean energy of $71.5 \pm 48.3$\,J, an end-effector position error of $2.64 \pm 1.04$\,cm, and an orientation error of $6.92 \pm 1.33^\circ$ -- within the \SI{4}{\centi\metre}/$8.6^\circ$ training tolerance. These results constitute a first step toward energy-aware reinforcement-learning-based arm reaching for humanoid robots.

2026-06-14T16:46:18Z Nestor N. Deniz Simon Parsons Fernando Auat Cheein http://arxiv.org/abs/2606.15915v1 2026-06-14T16:45:07Z

Accurate prediction of electrical power consumption is essential for energy-aware motion planning, battery management, and thermal monitoring in battery-powered humanoid robots. This letter presents a physics-based, linear-in-parameters model for the electrical power consumption of the seven-degree-of-freedom left arm of the Unitree~G1 humanoid robot. The proposed formulation combines actuator loss terms with a baseline-torque correction that captures changes in gravity-compensation load and enables accurate prediction of negative net power trajectories. Pairwise interaction terms are introduced to model power coupling during simultaneous multi-joint motion. Model parameters are identified from experimental data collected on a physical Unitree~G1 using onboard power measurements as the regression target. Across 897 trajectories covering single-joint and coordinated arm motions at multiple speed levels, the identified model achieves $R^2 = 0.933$ with an RMSE of 1.07 (W). Validation on 46 trajectories executed at previously unseen speeds yields $R^2 = 0.965$, demonstrating strong generalisation beyond the identification dataset. Analysis of the identified parameters reveals distinct power-consumption characteristics across the arm, with viscous friction dominating most joints (shoulder pitch and all three wrist joints), copper losses dominating shoulder yaw and the elbow, and shoulder roll uniquely dominated by Coulomb friction.

2026-06-14T16:45:07Z Nestor N. Deniz Sebastian Vega Simon Parsons Fernando Auat Cheein http://arxiv.org/abs/2606.06953v1 2026-06-05T06:33:09Z

We argue that high-quality motion data can steer tracking policies toward better optimization trajectories early in training. In this work, we introduce LIMMT (Less Is More for Motion Tracking). To our knowledge, this is the first data-centric study for physics-based humanoid motion tracking. We go beyond simply removing low-quality and erroneous clips, but define motion data quality through three dimensions: physics feasibility, diversity, and complexity. We show that even training with under 3% of AMASS yields better tracking performance than training with the full dataset. We further conduct data cleaning on the estimated web-sourced mocap data. Extensive experiments and analyses validate the effectiveness of our framework.

2026-06-05T06:33:09Z Accepted at ICML 2026 Yu Guan Zekun Qi Chenghuai Lin Xuchuan Chen Dairu Liu Wenyao Zhang Jilong Wang Xinqiang Yu He Wang Li Yi http://arxiv.org/abs/2605.31120v1 2026-05-29T10:30:03Z

We propose a new method for synthesizing physically-based swimming motions. Physically-based character animation aims to generate physically valid, controllable, and natural-looking motions which can respond to unexpected disturbances, where one dictating factor of difficulty is the complexity of the task, especially the level of sophistication of the required interactions with the environment. Existing research has succeeded in various tasks in static and dynamic environments. We push the difficulty further to swimming, which requires full-body coordination and continuous interactions with fluids, a new level of complexity when it comes to interacting with the environment. This complexity imposes challenges in learning control under volatile environmental forces, generalizing control to different environments and swimming styles, lack of data references, and prohibitively slow physical simulation which is inevitable during control learning. To this end, we propose SWIM, a new imitation method for swimming motions, which can learn from a single swimming motion and generalize to unseen environments, body conditions, and swimming styles. Extensive evaluation and comparison demonstrate that SWIM is data-efficient, stable, robust, and generalizable, outperforming alternative methods across multiple classes of tasks and metrics.

2026-05-29T10:30:03Z Binglun Wang Edmond S. L. Ho He Wang http://arxiv.org/abs/2605.26006v2 2026-06-02T14:18:24Z

Enabling physics-based humanoids to execute diverse behaviors from high-level textual commands remains a significant challenge. Existing methods typically follow either a two-stage paradigm that combines kinematic motion generation with physics-based tracking, or an end-to-end imitation-learning paradigm that directly generates actions from text. However, the former suffers from the inherent domain shift between kinematic generation and physics-based tracking, while the latter struggles with the substantial modality gap between textual commands and low-level actions, limiting effective semantic alignment. Notably, humanoid states encode rich motion dynamics that are more semantically aligned with textual descriptions than low-level actions, making them a natural basis for deriving behavioral intent. Building upon this insight, we propose MIND, a novel end-to-end diffusion framework for text-driven physics-based humanoid control that leverages behavioral intent as a semantic bridge between textual commands and low-level actions. At its core, MIND introduces a multi-scale intent diffusion mechanism, where a holistic intent predictor captures global behavioral dynamics to guide overall behavior synthesis, while an immediate intent predictor provides step-wise, fine-grained signals for local behavior refinement at each diffusion step. This hierarchical intent formulation imposes a structured inductive bias for humanoid control, improving semantic alignment and behavioral naturalness. Furthermore, MIND encodes humanoid states into a latent space to enable more effective semantic intent modeling. Extensive experiments demonstrate that MIND outperforms existing methods and synthesizes coherent, physically plausible, and semantically aligned humanoid behaviors from text commands. Project page: https://binlee26.github.io/MIND_page.

2026-05-25T16:23:10Z Bin Li Ruichi Zhang Han Liang Jingyan Zhang Juze Zhang Xin Chen Jingya Wang http://arxiv.org/abs/2605.22894v3 2026-09-04T08:58:08Z

Controlling physics-based humanoids from natural-language instructions is a critical step toward general-purpose embodied agents. However, existing methods remain constrained by a tension between semantic expressiveness and physical feasibility, often failing to jointly achieve faithful instruction following, high-quality motion, and stable long-horizon control. We propose SCRIPT, a scalable diffusion policy with a multi-stage training framework for language-driven physics-based humanoid control. The core of SCRIPT is a Joint Action-State-Text Diffusion Transformer (JAST-DiT), which represents actions, physical states, and text as dedicated token streams and couples them through joint attention, enabling direct interaction between language semantics and control dynamics. To stabilize autoregressive control, we introduce a nonlinear history conditioning mechanism, which preserves the dense recent context and samples increasingly sparse cues from long-term history. Beyond supervised imitation pre-training, we propose a post-training stage, further improving the performance using Reinforcement Learning with Hybrid Rewards (RLHR). By injecting learnable noise into the flow-sampling process, RLHR effectively improves motion quality and instruction following within closed-loop simulations using hybrid physical feedback and text rewards. Quantitative evaluations demonstrate that SCRIPT outperforms prior state-of-the-art methods, with gains across text alignment, motion quality, and physical realism metrics. Furthermore, scaling studies on the 1200-hour MotionMillion dataset demonstrate consistent performance gains with model scaling, highlighting SCRIPT's robust scalability for large-scale pre-training. Our code will be publicly available for future research.

2026-05-21T14:17:21Z Project page: https://zhanglele12138.github.io/SCRIPT/ Jingyan Zhang Han Liang Ruichi Zhang Bin Li Juze Zhang Xin Chen Jingya Wang Lan Xu Jingyi Yu http://arxiv.org/abs/2605.20373v1 2026-05-19T18:24:05Z

Building humanoid robots capable of generalizable whole-body loco-manipulation in the real world remains a fundamental challenge. Existing methods either rely on laborious task-specific reward engineering, rigidly replay reference motions that fail to generalize, or depend on costly teleoperation that limits scalability. While human videos capture diverse human behaviors, motion priors inferred from them are inherently imperfect, suffering from occlusion, contact artifacts, and retargeting errors that render them unsuitable for direct policy learning. To address this, we present SUGAR, a scalable data-driven framework that converts diverse human videos into deployable humanoid loco-manipulation skills, without any task-specific reward engineering or reference-motion conditioning at inference. SUGAR proceeds in three stages. First, a fully automated pipeline extracts kinematic interaction priors including human-object motion trajectories and contact labels from unstructured human videos. Second, a privileged physics-based refiner uses a unified mimic reward and progressive state pool to transform imperfect priors into physically feasible, high-fidelity skills. Third, refined skills are distilled into a hierarchical autonomous policy consisting of a command generator and a command tracker. We evaluate SUGAR on six representative loco-manipulation tasks in simulation and real-world humanoid hardware. Our method substantially outperforms reference-tracking baselines, and performance scales clearly with the amount of human video data. It also achieves zero-shot real-world transfer with reliable closed-loop execution, autonomous failure recovery, and stable long-horizon performance under external perturbations. Project Page: https://tianshuwu.github.io/sugar-humanoid/

2026-05-19T18:24:05Z Project Page: https://tianshuwu.github.io/sugar-humanoid/ Tianshu Wu Xiangqi Kong Yue Chen Qize Yu Hang Ye Jia Li Yizhou Wang Hao Dong http://arxiv.org/abs/2605.14462v1 2026-05-14T06:56:57Z

Recovering 4D human-object interaction (HOI) from monocular video is a key step toward scalable 3D content creation, embodied AI, and simulation-based learning. Recent methods can reconstruct temporally coherent human and object trajectories, but these trajectories often remain visual artifacts while failing to preserve stable contact, functional manipulation, or physical plausibility when used as reference motions for humanoid-object simulation. This reveals a fundamental interaction gap: HOI reconstruction should not stop at tracking a human and an object, but should recover the relation that makes their motion a coherent interaction. We introduce $\textbf{HA-HOI}$, a framework for reconstructing physically plausible 4D HOI animation from in-the-wild monocular videos. Instead of treating the human and object as independent entities in an ambiguous monocular 3D space, we propose a $\textit{human-first, object-follow}$ formulation. The human motion is recovered as the interaction anchor, and the object is reconstructed, aligned, and refined relative to the human action. The resulting kinematic trajectory is then projected into a physics-based humanoid-object simulation, where it acts as a teacher trajectory for stable physical rollout. Across benchmark and in-the-wild videos, $\textbf{HA-HOI}$ improves human-object alignment, contact consistency, temporal stability, and simulation readiness over prior monocular HOI reconstruction methods. By moving beyond visually plausible trajectory recovery toward physically grounded interaction animation, our work takes a step toward turning general monocular HOI videos into scalable demonstrations for humanoid-object behavior. Project page: https://knoxzhao.github.io/real2sim_in_HOI/

2026-05-14T06:56:57Z Yubo Zhao Yujin Chai Yunao Dong Chengfeng Zhao Zijiao Zeng Yuan Liu Chi-Keung Tang http://arxiv.org/abs/2604.20841v1 2026-04-22T17:59:55Z

Recent advances in video generative models enable the synthesis of realistic human-object interaction videos across a wide range of scenarios and object categories, including complex dexterous manipulations that are difficult to capture with motion capture systems. While the rich interaction knowledge embedded in these synthetic videos holds strong potential for motion planning in dexterous robotic manipulation, their limited physical fidelity and purely 2D nature make them difficult to use directly as imitation targets in physics-based character control. We present DeVI (Dexterous Video Imitation), a novel framework that leverages text-conditioned synthetic videos to enable physically plausible dexterous agent control for interacting with unseen target objects. To overcome the imprecision of generative 2D cues, we introduce a hybrid tracking reward that integrates 3D human tracking with robust 2D object tracking. Unlike methods relying on high-quality 3D kinematic demonstrations, DeVI requires only the generated video, enabling zero-shot generalization across diverse objects and interaction types. Extensive experiments demonstrate that DeVI outperforms existing approaches that imitate 3D human-object interaction demonstrations, particularly in modeling dexterous hand-object interactions. We further validate the effectiveness of DeVI in multi-object scenes and text-driven action diversity, showcasing the advantage of using video as an HOI-aware motion planner.

2026-04-22T17:59:55Z Project Page: https://snuvclab.github.io/devi/ Hyeonwoo Kim Jeonghwan Kim Kyungwon Cho Hanbyul Joo http://arxiv.org/abs/2605.20209v2 2026-07-18T16:31:33Z

Achieving precise, versatile whole-body character control in physics-based animation remains challenging. Recent diffusion-based policies generate rich and expressive motions but typically rely on gradient-based test-time guidance to satisfy task objectives, which is slow and can reduce robustness. We introduce NaP-Control (Navigating Diffusion Prior for Versatile and Fast Character Control), abbreviated as NaP. Our method uses reinforcement learning to manipulate the latent noise of a task-agnostic diffusion policy prior, steering it toward task-specific behaviors for fast, robust control with high motion fidelity. In contrast to methods that rely solely on offline training, NaP interacts with the environment during training to correct motions and optimize task rewards, improving success rates and enabling adaptation to challenging scenarios. By directly predicting task-optimized diffusion noise, NaP eliminates iterative guidance during denoising and enables efficient inference. Experiments show that NaP attains higher success rates and faster inference while preserving natural motion across diverse tasks.

2026-04-15T14:51:32Z ECCV 2026. Project page: https://chiawenchen.github.io/nap-control-project/ Chia-Wen Chen Yan Wu Korrawe Karunratanakul Siyu Tang http://arxiv.org/abs/2604.07984v1 2026-04-09T08:55:16Z

Motion tracking has been an important technique for imitating human-like movement from large-scale datasets in physics-based motion synthesis. However, existing approaches focus on tracking either single character or a particular type of interaction, limiting their ability to handle contact-rich interactions. Extending single-character tracking approaches suffers from the instability due to the challenge of forces transferred through contacts. Contact-rich interactions requires levels of control, which places much greater demands on model capacity. To this end, we propose a robust tracking method based on progressive neural network (PNN) where multiple experts are specialized in learning skills of various difficulties. Our method learns to assign training samples to experts automatically without requiring manually scheduling. Both qualitative and quantitative results show that our method delivers more stable motion tracking in densely interactive movements while enabling more efficient model training.

2026-04-09T08:55:16Z Xiaotang Zhang Ziyi Chang Qianhui Men Hubert P. H. Shum http://arxiv.org/abs/2604.05394v1 2026-04-07T03:47:14Z

Physics-based character animation has become a fundamental approach for synthesizing realistic, physically plausible motions. While current data-driven deep reinforcement learning (DRL) methods can synthesize complex skills, they struggle to reproduce exaggerated, stylized motions, such as instantaneous dashes or mid-air trajectory changes, which are required in animation but violate standard physical laws. The primary limitation stems from modeling the character as an underactuated floating-base system, in which internal joint torques and momentum conservation strictly govern motion. Direct attempts to enforce such motions via external wrenches often lead to training instability, as velocity discontinuities produce sparse, high-magnitude force spikes that prevent policy convergence. We propose Assistive Impulse Neural Control, a framework that reformulates external assistance in impulse space rather than force space to ensure numerical stability. We decompose the assistive signal into an analytic high-frequency component derived from Inverse Dynamics and a learned low-frequency residual correction, governed by a hybrid neural policy. We demonstrate that our method enables robust tracking of highly agile, dynamically infeasible maneuvers that were previously intractable for physics-based methods.

2026-04-07T03:47:14Z Zhiquan Wang Bedrich Benes