Physical AI

Holiday Robots tactile sensors let a robot feel paintbrush contact

Holiday Robots tactile sensors let a robot feel paintbrush contact

DART turns SAM3 into a real-time open-vocabulary detector at 55.8 AP on COCO

DART turns SAM3 into a real-time open-vocabulary detector at 55.8 AP on COCO

Riemann-1.0 trains a World Action Model on 200k hours of human video

Riemann Dynamics introduces Riemann-1.0, a World Action Model trained on more than 200,000 hours of egocentric human video combined with gripper data and robot trajectories, targeting general-purpose robot manipulation, world simulation, and action generation.

WilLaGS: Latent-Conditional 3D Appearance Fields for Robust Gaussian Splatting In-the-Wild

3D Gaussian Splatting (3DGS) delivers real-time and high-fidelity rendering but remains challenged by unconstrained in-the-wild scenes, where drastic appearance variations and transient objects violate multi-view consistency. Existing methods are fundamentally limited by independent and discrete embeddings that struggle to capture continuous environmental changes or model spatially-varying local illumination. To address these limitations, we propose WilLaGS, a unified framework for robust 3D scene reconstruction and generative appearance synthesis under unconstrained settings. Specifically, we introduce a generative appearance model where a β-VAE learns a structured and continuous manifold of global appearance. Conditioned on the latent code, we construct a 3D neural appearance field that generates dynamic Tri-Plane features to encode spatially-varying local illumination effects. Furthermore, to suppress transient artifacts, we present a self-supervised perceptual masking mechanism that leverages a Teacher-Student (EMA) architecture to derive a stable scene consensus, robustly identifying inconsistent regions via perceptual discrepancies. Extensive experiments on multiple datasets demonstrate that WilLaGS achieves state-of-the-art performance in reconstruction quality and novel view appearance synthesis, while maintaining real-time rendering efficiency.

Yuhao Bai, Qianqiu Tan, Lilong Chen

Contact-Guided Exploration for Non-Prehensile Locomanipulation with Multi-Critic RL

The paper turns 25 grasp-algorithm candidates into a retractable exploration objective, separates task, exploration, and regularization signals with three value heads, and schedules their advantages during training. The full method reaches 94.1% simulation success with 4.4% tipover and transports unseen IKEA objects in 40/58 zero-shot hardware trials.

Simone Tolomei, Mayank Mittal, Franco Angelini

Koala gripper pairs handheld teleoperation with a robotic gripper for demonstration collection

The Koala gripper is a co-designed system that pairs a handheld data-collection device with a robotic gripper, letting a single operator record task demonstrations easily. It uses three controllable degrees of freedom and force-optimized triggers to lower the barrier for collecting robot manipulation demonstrations.

Meta Reality Labs open-sources Project SuperDex, a contact-first dexterous manipulation simulator

Project SuperDex is an open-source, contact-first physics engine from Meta Reality Labs for the hard parts of dexterous manipulation: multi-finger grasps, in-hand reorientation, soft contact, and tactile sensing. It supports VR teleoperation for low-cost demonstration collection and Gym-style RL interfaces for more reliable robot-hand research.

SOLO: Stable Omni-terrain Long-Horizon Perceptive Humanoid Locomotion

Humans traverse complex terrain over long distances without losing balance, whereas perceptive humanoid policies become fragile as perception and control errors accumulate. We present SOLO, a unified framework addressing two compounding causes of this long-horizon fragility: dense terrain reconstruction smooths action-critical details, and pointwise imitation lacks temporal credit assignment. Its Query Reconstructor (QR) uses Fourier-encoded cell queries to retrieve spatially specific evidence from depth-proprioception tokens, preserving sharp terrain boundaries. Trajectory-Aware MSE (TA-MSE) Distillation adds next-state teacher-student disagreement to the PPO reward, enabling Generalized Advantage Estimation to propagate future disagreement penalties to preceding actions. In simulation, QR reduces height-map L1 error by factors of 3.3-4.0, while TA-MSE surpasses PPO and MSE+PPO in curriculum progression. On stress-test terrains, SOLO achieves 97.5% mean traversal success and 96% stepping-stone success, versus 75.0-75.6% and 0-3% for dense-reconstructor variants. Deployed zero-shot with only a chest-mounted depth camera and proprioception, SOLO completes a continuous 1.5-km outdoor route and an indoor mixed-terrain course. Project page: https://sunpihai-up.github.io/solo/

Pihai Sun, Gang Han, Jingkai Sun

RoboGesture: Real-Time Semantic-aligned Co-Speech Gestures Generation for Humanoid Interaction

Enabling humanoid robots to respond to human speech with synchronized and semantically meaningful gestures is fundamental to natural human-robot interaction. However, this task faces three critical barriers: the scarcity of semantically rich datasets, the "modality eclipse" where models ignore audio cues in favor of kinematic inertia, and the sim-to-real gap regarding physical safety. We propose RoboGesture, a robot-centric framework that co-designs data, modeling, and control to power a complete interactive human-humanoid system in which the robot listens, responds, and gestures in real time. We first establish the RoboGesture dataset featuring over 300 gesture categories and develop an automated pipeline to synthesize large-scale collision-free, robot-specific audio-motion pairs. Our architecture features a Hierarchical Semantic-Acoustic Aligner that extracts multi-granular prosodic and semantic cues directly from raw audio tokens. These cues drive a Streaming Conditional Motion Generator based on a diffusion transformer with conditional flow matching. To ensure high responsiveness, we introduce Anti-Inertia CFG Masking, which prevents the model from collapsing into repetitive historical patterns by compelling it to proactively mine control signals from the audio modality. Finally, an MPC-based safety filter ensures real-time, collision-free execution on physical hardware. Experiments on a Unitree G1 humanoid demonstrate that RoboGesture generates safer, more rhythmic, and more semantically appropriate responses compared to state-of-the-art baselines.

Wang, Zifan, Ren, Ziang, Shi, Pengyang

Meta Open-Sources Project SuperDex: A Unified Dexterous Manipulation Platform with a Contact-First Physics Engine and Zero-Shot Sim2Real

Meta Reality Labs Research open-sourced Project SuperDex, a unified dexterous-manipulation simulation platform built on a custom contact-first physics engine with soft-body/rod/non-convex contact support, VR teleoperation for synthetic data, and a Gymnasium-style RL stack that achieved zero-shot sim2real shape sorting.

Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization

Zero-shot cross-task generalization, where a policy must execute manipulation tasks never seen during training, remains a central challenge in robot learning. In large language models, a novel task can be performed simply by specifying it in the context, without any parameter update. This form of in-context learning (ICL) turns generalization into a problem of task specification. To achieve cross-task generalization, we bring this paradigm to robotic manipulation, and argue that the natural task specification for manipulation is a human video: unlike language, it provides rich visual cues about the intended task evolution. We present Zero-WAM, a causal video-action model that executes unseen tasks by following in-context human video guidance. To address the scarcity of task-rich paired human-robot data, we propose an automatic pipeline that converts task-sampled robot trajectories into semantically matched human videos, yielding HumanGen, a dataset of 74.2K human-robot ICL pairs across 8.6K tasks. For model training, we further introduce an in-context future chunk prediction (IFP) objective that suppresses shortcuts learned from seen tasks and forces the policy to draw task information from the video prompt. On seven unseen tasks in RoboTwin 2.0 simulation, Zero-WAM achieves a 47.0% average success rate, an absolute improvement of 29.5 percentage points over the strongest video-action baseline. In real-world evaluations, it follows human video guidance to generalize to unseen task configurations involving multi-object scenes, long-horizon manipulation, and fine-grained insertion.

Jiaming Zhou, Qihang Zhang, Gangwei Xu

LAC: Linear and Angular Compliance for Humanoid Whole-body Control

LAC is a general humanoid whole-body controller that simultaneously realizes commanded linear and angular compliance for wrenches applied to the upper body. Sampled force and couple events imposed on contact frames from human interaction data synthesize a large-scale compliant-response dataset; teacher-student RL then trains a single policy to track compliant motions under external wrenches, with sim and real experiments showing monotonic stiffness modulation and teleoperated loco-manipulation.

Yang Liu, Zhongkai Gu, Wei Zhu