ロボティクスとフィジカルAIの最新論文と、それぞれが産業にもたらす意味。
プレプリントとして公開された本研究では、TD-M(PC)2を基盤に、批評家の学習目標を多段階化するMTD、計画時の終端価値に不確実性ペナルティを加えるATE、実現報酬で重み付けした模倣を行うRADを組み込んだPL-MPCを提案した。HumanoidBenchのbalance-hardでTotal Average Returnが98±18から387±255へ、hurdleで199±13から466±200へ向上し、実機のKUKA IIWA14によるレンチとナットの位置合わせでもTD-M(PC)2を上回る成功率を報告した。
本論文は、四脚ロボットが未踏地形で得た接触指標を、DINOv3の視覚特徴から不確実性付きで予測する継続学習パイプラインを提案したプレプリントである。逐次的な実機データストリームで、履歴検証ゲート付きリプレイはゲートなしリプレイに比べ最終アンカーNLL劣化を23.1%相対低減し、新地形への適応はほぼ同等だった。この手法は、地形の見た目ではなくロボット自身の接触応答に基づく走破性評価を可能にする点で重要である。
このプレプリントは、VLAのモデル推論とロボット実行系の遅延を実測し、Flow Matchingの速度場が終端付近で方向補正に集中することを示した。その上で標準の10NFEから2NFEへ削減する2段階非一様デノイジングを提案し、推論時間を61.557msから21.956msに短縮した。双腕Tシャツ折りタスクで6種類のリアルタイム実行手法を比較し、学習ベースではLegato、学習不要ではTemporal Smoothingが最高で、2段階推論を組み合わせると推論コストは大幅に減るが成功率は小幅に低下した。
強化学習で訓練したアクタークリティックとセンサ予測モデルをPAC-NMPCに統合し、未知環境での知覚ベース航法に有限時間の確率的衝突回避保証を与える手法を提案した。固定翼機の実機実験では成功率80パーセントを達成し、RL単独方策や地図とA*を用いるPAC-NMPCの40パーセントを上回った。本論文はarXivプレプリントであり、査読済みではない。
Yinwang Intelligent Technology の研究チームは、視覚言語、動画、行動の専門家を非対称な注意機構で統合する EWAM を開発した。浅層では意味理解、中層では未来フレーム予測、深層では行動生成という層別の計算分担が自然に生じ、ロボット軌道と人の一人称動画で事前学習したところ RoboTwin の clean-to-random で 72.1%、LIBERO で平均 98.8% を達成し、実機でも既存手法を上回った。本論文は査読前のプレプリントである。
Accurate human motion prediction is crucial for robotic systems operating around people, particularly in complex indoor spaces. In this study, we assess the relative importance of different sources of information in indoor motion prediction with a human motion diffusion model.
Long-horizon robotic tasks are vulnerable to unexpected environmental changes that can render planned actions ineffective or unsafe. To address this, robots must detect such changes as they occur, interpret their impact, and adjust their actions accordingly.
World-Action Models (WAMs) couple visual dynamics with action prediction, bringing the rich priors of pretrained video models to robotic manipulation. However, their multi-view interfaces typically tile images or concatenate tokens, leaving the geometric relationships among synchronized cameras implicit.
Vision-language-action (VLA) models have advanced robotic manipulation, but their zero-shot generalization in new tasks and environments remains limited, and their reliance on specialized training keeps them from benefiting directly from rapidly advancing general-purpose vision-language models (VLMs). In parallel, recent agentic robotic systems leverage VLMs for high-level reasoning or coding agents for robot control, but often depend on extensive external models and tools, introducing additional complexity and cost.
Robot policies are frequently trained from human corrections, yet teleoperating a robot to provide corrections is burdensome, and human demonstrators are not always optimal. We propose Blended DAgger (BlenDAgger), an approach for collecting data to train imitation learning policies by using shared control to blend the policy's and demonstrator's actions during interventions.
Egocentric human demonstrations offer an accessible source of task experience, but differences in body scale and controller response, together with missing robot states, limit their value as humanoid training supervision. We present EgoAlign, a data-construction framework that converts these demonstrations into action and state supervision compatible with a general-purpose, continuous whole-body controller, without collecting physical-robot demonstrations.
World-action models jointly learn robot policies and predict future observations, making the representation space an interface between control and prediction. We study the design of this space through controlled comparisons, finding that neither reconstruction fidelity nor pre-trained perceptual features alone ensure effective policy learning.
Monocular RGB video provides an accessible source of human demonstrations for upper-body robot motion, yet video-driven human-to-robot transfer remains challenging because body and hand motion are recovered at different spatial scales, human and robot kinematics differ substantially, and fine distal motion is difficult to preserve across embodiments. We present a geometry-preserving motion-retargeting framework that integrates unified body--hand reconstruction with morphology-independent geometric transfer.
Contingency games enable agents to anticipate and plan for other agents' hypothetical intents by constructing trajectories with a shared prefix and intent-dependent branches. While contingency games capture intent uncertainty, existing formulations rely on a single branching time, oversimplifying interactions in which different agents' intentions are revealed at different times.
Visual Language Action (VLA) models offer unprecedented generalization for autonomous robots; however, their real-world deployment is frequently bottlenecked by unreliable execution and the prohibitive computational cost of fine-tuning for specific robot embodiments and tasks. To bridge this gap, we propose WayFinder, an end-to-end, closed-loop hierarchical VLA framework that circumvents the need for fine-tuning by decoupling high-level task reasoning from low-level kinematic control.
Average performance on routine driving benchmarks does not establish planner reliability under rare, safety-critical hazards. We proposed ExceptionDrive, a counterfactual planning benchmark that uses VLM-assisted screening, localized multi-view editing, and quality auditing to insert hazards into real nuScenes scenes while preserving their context.
Robot policies increasingly incorporate semantic reasoning and future-world prediction, yet combining these capabilities does not guarantee that local predictions and actions remain aligned with task progress. We introduce CogWAM, a cognition-guided world-action model that establishes an explicit semantic interface between task reasoning and world-action learning through a persistent Semantic State, which stores completed task events and the active subtask.
We present Pow3R-SLAM, a real-time RGB-D simultaneous localization and mapping (SLAM) system that uses Pow3R for tracking and mapping. Inspired by MASt3R-SLAM, a recent work on monocular SLAM using two-view 3D reconstruction priors, we extend the work to incorporate depth as a prior on the network's prediction, rather than as geometry to fuse.
Vision-language-action and world-action models have demonstrated impressive capabilities in robotics, yet generalization to unseen tasks remains challenging. More recently, general-purpose multimodal agents have shown great potential for zero-shot robotic task solving.
Adaptive Cruise Control (ACC) systems are typically calibrated for an average driver, often resulting in a mismatch between vehicle behavior and individual expectations during time-critical maneuvers such as highway overtaking. When the ACC is perceived as too conservative and inconsistent, drivers intervene through throttle overrides, providing implicit feedback on the system's behavior.
論文は arXiv のロボティクス分野から取得しています。当社の要約が未作成の場合は、要旨の冒頭を表示します。