ChainedDiffuser: Unifying Trajectory Diffusion and Keypose Prediction for Robotic Manipulation

ChainedDiffuser: Unifying Trajectory Diffusion and Keypose Prediction for Robotic Manipulation
复制标题

DOI:
--
复制
发表时间:
2023
期刊:
--
影响因子:
--
通讯作者:
Zhou Xian;N. Gkanatsios;Théophile Gervet;Tsung-Wei Ke;Katerina Fragkiadaki
Zhou Xian;N. Gkanatsios;Théophile Gervet;Tsung-Wei Ke;Katerina Fragkiadaki
中科院分区:
其他
文献类型:
--
作者:
Zhou Xian;N. Gkanatsios;Théophile Gervet;Tsung-Wei Ke;Katerina Fragkiadaki

文献摘要

相似文献

我们提出了ChainedDiffuser,一种统一了动作关键点预测和轨迹扩散生成的策略体系结构,用于从演示中学习机器人操作。我们的主要创新是使用基于全局变换的动作预测器来预测关键帧上的动作,这是一项需要多模式语义场景理解的任务,并使用局部轨迹散射器来预测连接预测的宏观动作的轨迹段。ChainedDiffuser在已建立的操纵基准上创造了新的纪录,并超过了使用运动规划器进行轨迹预测的最先进的关键姿势(宏观动作)预测模型,以及不预测关键帧宏观动作的轨迹扩散策略。我们在模拟和真实环境中进行了实验,并展示了ChainedDiffuser解决涉及与不同对象交互的广泛操作任务的能力。
: We present ChainedDiffuser, a policy architecture that unifies action keypose prediction and trajectory diffusion generation for learning robot manipulation from demonstrations. Our main innovation is to use a global transformer-based action predictor to predict actions at keyframes, a task that requires multi-modal semantic scene understanding, and to use a local trajectory diffuser to predict trajectory segments that connect predicted macro-actions. ChainedDiffuser sets a new record on established manipulation benchmarks, and outperforms both state-of-the-art keypose (macro-action) prediction models that use motion planners for trajectory prediction, and trajectory diffusion policies that do not predict keyframe macro-actions. We conduct experiments in both simulated and real-world environments and demonstrate ChainedDiffuser’s ability to solve a wide range of manipulation tasks involving interactions with diverse objects.