研究人员正在开发新方法,通过结合时间上下文和视觉前瞻性来改进机器人操控。PACT-WAM 使用紧凑的时间编码来预测动作轨迹和视觉结果,在各种任务上实现了高成功率,尤其是在增强了提案审查组件后。同样,TEMPO 通过增加运动摘要和本体感受历史来增强现有模型,以解决运动模糊和状态别名问题,从而解决了动态操控的局限性。另一种方法“Acting in Meters”引入了一个度量交互框架,该框架在物理空间中对物体和场景交互进行建模,以优化动作预测。最后,正在探索能量正则化模仿学习,以优化机器人策略以实现物理上高效的运动,减少机械功,同时略微提高任务成功率。
AI
arXiv:2506.12374v3 Announce Type: replace-cross Abstract: Natural-language manipulation instructions specify the task goal but leave the underlying robot trajectory unspecified. We present AntiGrounding, a visual action-selection framework built around a dual geometric-visual tra…
arXiv cs.AI
TIER_1English(EN)·Kaipeng Fang, Weiqing Liang, Yuyang Li, Ji Zhang, Pengpeng Zeng, Heng Tao Shen, Jingkuan Song, Lianli Gao·
arXiv:2601.19406v2 Announce Type: replace-cross Abstract: Real-robot demonstrations are prohibitively expensive, while simulation data and real-world human demonstrations are both scalable but each leaves a distinct gap: simulation suffers from a sim-to-real visual gap, and human…
arXiv cs.AI
TIER_1English(EN)·Jing Jiang, Yue Yang, Xinkai Jiang, Gedas Bertasius, Daniel J. Szafir, Rudolf Lioutikov·
arXiv:2609.19413v1 Announce Type: cross Abstract: Robot manipulation policies are improving quickly, and real-robot evaluation remains the standard evidence for that progress. It still relies on a human to reset the scene between rollouts, which consumes operator time and leaves …
arXiv cs.AI
TIER_1English(EN)·Zitai Huang, Taiyi Su, Jian Zhu, Jianjun Zhang, Chong Ma, Tianbin Liu, Weiyi Lu, Yi Xu, Hanli Wang·
arXiv:2609.19974v1 Announce Type: cross Abstract: Long-horizon robot manipulation requires not only stable local visuomotor control, but also continuous target tracking and reliable task progress assessment throughout execution. This challenge becomes particularly critical when m…
arXiv:2602.15882v2 Announce Type: replace-cross Abstract: Robot manipulation uses temporal context to select actions and visual foresight to assess their consequences, yet dense representations of past and future observations incur substantial processing costs. We introduce PACT-…
arXiv:2609.18243v1 Announce Type: cross Abstract: Vision-Language-Action models and World-Action Models have advanced language-conditioned robotic manipulation, yet often leave metric relations among actions, objects, and scene geometry implicit. Human manipulation combines seman…
Vision-Language-Action models and World-Action Models have advanced language-conditioned robotic manipulation, yet often leave metric relations among actions, objects, and scene geometry implicit. Human manipulation combines semantic understanding of task-relevant objects with sp…
This paper studies energy-aware manipulation as a physically grounded learning problem. We define a joint-space mechanical-work proxy from joint torque and angular displacement, and train a differentiable energy predictor that estimates this work from robot states and actions. Th…
arXiv cs.LG
TIER_1English(EN)·Zhenyang Feng, Jimin Heo, Erik B. Sudderth, Unnat Jain·
arXiv:2609.16864v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have achieved impressive performance in quasi-static manipulation, but struggle in dynamic manipulation tasks because they operate on a single observation at inference time. We identify two repr…
Multi-finger dexterous manipulation relies on stable hand-object interactions, yet these interactions are partially observable in practice. Visual observations are often occluded by the hand, tactile sensors introduce hardware-specific modalities and calibration burdens, and exis…
arXiv:2609.18164v1 Announce Type: cross Abstract: This paper studies energy-aware manipulation as a physically grounded learning problem. We define a joint-space mechanical-work proxy from joint torque and angular displacement, and train a differentiable energy predictor that est…