News & Research

arXiv:2506.01568v4 Announce Type: replace-cross Abstract: Being able to solve a task in diverse ways makes agents more robust to task variations and less prone to local optima. In this context, constrained diversity optimization has become a useful reinforcement learning (RL) framework for training a set of diverse agents in parallel. However, existing constrained-diversity RL methods often under-explore in complex tasks such as robot manipulation, resulting in limited behavioral diversity. We address this with a two-stage curriculum that introduces a spline-based trajectory prior as an inductive bias to produce diverse, high-reward behaviors in an initial stage, and then distills these behaviors into reactive, step-wise policies in a second stage. In our empirical evaluation, we provide novel insights into challenges of diversity-targeted training and show that our curriculum increases the diversity of learned skills while maintaining high task performance.

arXiv:2406.01763v5 Announce Type: replace-cross Abstract: Contact-Implicit Trajectory Optimization (CITO) is a powerful framework for planning motions of robots that interact with complex environments, but its convergence behavior remains difficult to characterize. Existing formulations either rely on off-the-shelf nonlinear programming solvers whose guarantees require constraint qualifications that are hard to verify for contact-rich systems, or require differentiable explicit dynamics maps that are difficult to formulate in the presence of impacts, changing contact modes, and geometric non-smoothness. This paper studies CITO for a broader class of constraint-rich dynamic systems formulated through implicit physics constraints. By exploiting maximal-coordinate structure, penalty relaxations of equality and inequality constraints, and finite-horizon Hamiltonian bounds, we prove global convergence in the numerical-optimization sense for a specific line-search Sequential Quadratic Progra

arXiv:2604.05498v2 Announce Type: replace Abstract: World Action Models (WAMs) have emerged as a promising paradigm for robotic manipulation, enabling physical interaction across diverse tasks and environments. However, their ability to directly follow high-level instructions and execute physical actions also creates potential safety risks, as adversarially designed instructions may induce unsafe robot behaviors. To systematically assess these risks, we propose JailWAM, the first jailbreak evaluation framework for WAMs. In JailWAM, we integrate three key innovations: Firstly, to address the difficulty of evaluating heterogeneous low-level action outputs, we introduce Visual-Trajectory Mapping, which transforms model-specific actions into unified visual trajectory representations, thereby facilitating consistent risk assessment across WAM architectures. Secondly, to provide efficient and fine-grained assessment of physical risks, we develop a Risk Discriminator supervised by three safet

arXiv:2604.03781v2 Announce Type: replace Abstract: Colorectal cancer screening critically depends on colonoscopy, yet existing platforms offer limited support for systematically studying the coupled dynamics of operator control, instrument motion, and visual feedback. This gap restricts reproducible closed-loop research in robotic colonoscopy, medical imaging, and emerging vision-language-action (VLA) learning paradigms. To address this challenge, we present OpenRC, an open-source modular robotic colonoscopy framework that retrofits conventional scopes while preserving clinical workflow. The framework supports simultaneous recording of video, operator commands, actuation state, and distal tip pose. We experimentally validated motion consistency and quantified cross-modal latency across sensing streams. Using this platform, we collected a multimodal dataset comprising 1,894 teleoperated episodes ~19 hours across 10 structured task variations of routine navigation, failure events, and r

arXiv:2604.03181v2 Announce Type: replace Abstract: Robotic manipulation requires understanding both the 3D spatial structure of the environment and its temporal evolution, yet most existing policies neglect one or both aspects. They often rely on 2D visual observations or backbones pretrained on static image--text pairs, which leads to high data requirements and limited comprehension of environment dynamics. To address this, we introduce SpatialVAM, the first 3D Video Action Model that simultaneously predict spatial-aware multi-view heatmap videos and RGB videos. Our key insight is that this design naturally injects 3D information into video foundation models while aligning the representation format between video pretraining and action finetuning. Extensive experiments demonstrate that SpatialVAM enables data-efficient, robust, generalizable, and interpretable manipulation. With only ten demonstration trajectories and no additional pretraining, SpatialVAM handles challenging long-hori

arXiv:2603.15605v2 Announce Type: replace Abstract: Autonomous exploration in unknown environments typically relies on onboard state estimation for localisation and mapping. Existing exploration methods primarily maximise coverage efficiency, but often overlook that visual-inertial odometry (VIO) performance strongly depends on the availability of robust visual features. As a result, exploration policies can drive a robot into feature-sparse regions where tracking degrades, leading to odometry drift, corrupted maps, and mission failure. We propose a hierarchical perception-aware exploration framework for a stereo-equipped unmanned aerial vehicle (UAV) that explicitly couples exploration progress with feature observability. Our approach (i) associates each candidate frontier with an expected feature quality using a global feature map, and prioritises visually informative subgoals, and (ii) optimises a continuous yaw trajectory along the planned motion to maintain stable feature tracks.

arXiv:2602.11143v3 Announce Type: replace Abstract: Humanoid locomotion has advanced rapidly with deep reinforcement learning (DRL), enabling robust feet-based traversal over uneven terrain. Yet platforms beyond leg length remain largely out of reach because current RL training paradigms often converge to jumping-like solutions that are high-impact, torque-limited, and unsafe for real-world deployment. To address this gap, we propose APEX, a system for perceptive, climbing-based high-platform traversal that composes terrain-conditioned behaviors: climb-up and climb-down at vertical edges, walking or crawling on the platform, and stand-up and lie-down for posture reconfiguration. Central to our approach is a generalized ratchet progress reward for learning contact-rich, goal-reaching maneuvers. It tracks the best-so-far task progress and penalizes non-improving steps, providing dense yet velocity-free supervision that enables efficient exploration under strong safety regularization. Bas

arXiv:2511.07820v4 Announce Type: replace Abstract: Despite the rise of billion-parameter foundation models trained across thousands of graphical processing units (GPUs), similar scaling gains have not been shown for humanoid control. Current neural controllers for humanoids remain modest in size, target a limited set of behaviors, and are trained on a handful of GPUs. We show that scaling model capacity, data, and compute yields a generalist humanoid controller capable of natural, robust whole-body movements. We position motion tracking as a scalable task for humanoid control, leveraging dense supervision from diverse motion-capture data to acquire human motion priors without manual reward engineering. We build a foundation model for motion tracking by scaling along three axes: network size (1.2M to 42M parameters), dataset volume (100M+ frames from 700 hours of motion capture), and compute (21k GPU hours). Beyond demonstrating the benefits of scale, we further show downstream utility

arXiv:2509.24928v2 Announce Type: replace Abstract: This work introduces an adaptive Bayesian algorithm for real-time trajectory prediction via intention inference, where a target's intentions and motion characteristics are unknown and subject to change. The method concurrently estimates two critical variables: the target's current intention, modeled as a Markovian latent state, and an intention parameter that describes the target's adherence to a shortest-path policy. By integrating this joint update technique, the proposed algorithm maintains robustness against abrupt intention shifts in trajectory prediction and unknown motion dynamics. A sampling-based trajectory prediction mechanism then exploits these adaptive estimates to generate probabilistic forecasts with quantified uncertainty. We validate the algorithm through numerical experiments: Ablation studies of two cases, and a 500-trial Monte Carlo analysis; Hardware demonstrations on quadrotor and quadrupedal platforms. Experimen

arXiv:2508.17464v2 Announce Type: replace Abstract: Brain-body co-optimization remains a challenging problem. To understand and overcome its challenges, we exhaustively map a morphology-fitness landscape: we train controllers for each morphology in a design space of 1,305,840 voxel-based soft robots. We show that this design space constitutes a good model for studying brain-body co-optimization and that our mapping roughly captures its landscape. Complete knowledge of the landscape lets us analyze how evolutionary co-optimization algorithms unfold. We find that the tested algorithms cannot consistently find near-optimal solutions: the search, at times, gets stuck on morphologies one mutation away from better ones, because it regularly undervalues individuals with newly mutated bodies and eliminates promising morphologies. On the other hand, co-optimizing morphology and control creates useful goal-switching, yielding morphology-controller pairs whose performance cannot be reached by opt

arXiv:2608.13489v1 Announce Type: cross Abstract: We present \textbf{DreamX-Phi 1.0}, an action-conditioned video world model for robotic manipulation that, given an observed frame, a language instruction, and a prescribed action sequence comprising end-effector poses and gripper states, predicts the resulting future observations. Yet realism alone does not guarantee faithfulness: a convincing rollout can still move the wrong arm or lose the manipulated object. To ensure the prediction respects each arm's commanded path, we inject per-arm $\mathrm{SE}(3)$ transformations into attention via \textbf{PRoPE-style geometric encoding}, preserving arm identity and rigid-motion structure. Action control alone does not fully constrain scene geometry or the evolution of small manipulated objects. We therefore add a lightweight \textbf{depth branch} for scene-level geometry and use \textbf{SAM3 masks} with a frozen \textbf{V-JEPA teacher} to maintain object consistency throughout grasping. We fur

arXiv:2608.13028v1 Announce Type: cross Abstract: Human-to-robot (H2R) object handover is a fundamental capability for human-robot collaboration, yet progress is hindered by the scarcity of large-scale, human-centric datasets and the significant sim-to-real gap. To address these challenges, we introduce Hand2Bot, an RGB-D video dataset that provides rich contextual information such as body posture and facial expressions, specifically collected for handover scenarios with real-world noise patterns. We further propose PassGen, a generative pipeline that leverages stable video diffusion and an Intention-Aware Temporal Face Encoder to synthesize realistic handover sequences while ensuring hand-object consistency. To bridge the sim-to-real gap, we implement a morphology-based depth editing strategy that replicates realistic sensor noise found in physical depth maps. Experimental evaluations demonstrate that our framework achieves high intention identification accuracy and low false trigger