用扩散模型+能量优化，让机器人双手协同翻转物体更顺滑、成功率更高。
Grasp, Handover, Rotate: Bimanual Object Reorientation via Compositional Diffusion and Energy-Based Optimization
- 分步组合扩散与能量模型，联合优化抓取、交接和重抓
- 成功率超基线20%以上，轨迹平滑度提升37%
- 适合复杂场景下的双臂操作任务，可直接用于真实机器人
双臂物体重定向——从抓取、双手交接至目标姿态放置——在初始抓取无法直接放置时极具价值，常见于碰撞、运动学约束或最终朝向不佳的情况。然而，在多重目标冲突下实现该任务仍具挑战。本文提出BiCompoDiff，一种组合式扩散与基于能量的优化框架，联合优化抓取选择、交接过程、重抓及运动规划，满足多种约束。通过将预训练的抓取扩散模型与双臂规划能量模型（EBMs）结合，在逆向扩散过程中注入梯度引导，以确保避障、轨迹平滑（通过可微逆运动学）、交接可行性及重抓安全。采用退火马尔可夫链蒙特卡洛采样进一步在复合能量景观上精炼抓取姿态。在多样化模拟家居重定向任务中，BiCompoDiff成功率较强基线提升20%以上，轨迹平滑度（以关节位移衡量）最高提升37%。真实世界验证表明其具备良好的仿真到现实迁移能力，可在复杂场景中稳定运行。
原文摘要 · Abstract (English)
Bimanual object reorientation - picking an object, handing it over between two arms, and placing it in a desired target pose - is valuable when direct placement from the initial grasp is infeasible due to collisions, kinematic constraints, or poor final orientation. However, achieving this under multiple competing objectives remains challenging. We introduce BiCompoDiff, a compositional diffusion and energy-based framework that jointly optimizes grasp selection, handover, regrasp, and motion planning under multiple constraints. By combining a pretrained grasp diffusion model with bimanual planning energy-based models (EBMs), our method injects gradient guidance during reverse diffusion to enforce collision avoidance, trajectory smoothness (via differentiable inverse kinematics), handover feasibility, and regrasp safety. Annealed MCMC sampling further refines grasp poses over the composite energy landscape. Experiments across diverse simulated household reorientation tasks demonstrate that BiCompoDiff achieves over 20% higher success rates and up to 37% smoother trajectories (measured by joint displacement) compared to strong sampling-based baselines. Real-world validation confirms effective sim-to-real transfer and robust performance on challenging scenes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。