Humans can imagine goal states during planning and perform actions to match
those goals. In this work, we propose Imagination Policy, a novel multi-task
key-frame policy network for solving high-precision pick and place tasks.
Instead of learning actions directly, Imagination Policy generates point clouds
to imagine desired states which are then translated to actions using rigid
action estimation. This transforms action inference into a local generative
task. We leverage pick and place symmetries underlying the tasks in the
generation process and achieve extremely high sample efficiency and
generalizability to unseen configurations. Finally, we demonstrate
state-of-the-art performance across various tasks on the RLbench benchmark
compared with several strong baselines.

我们提出了一种新颖的多任务关键帧策略网络 —— 想象策略，用于解决高精度拾取和放置任务。通过生成点云来想象所需的状态，然后使用刚性动作估计将其转化为动作，将动作推理转化为局部生成任务。我们利用任务中的拾取和放置对称性在生成过程中实现极高的样本效率和对未见配置的泛化能力。最后，与几个强基准方法相比，我们在 RLbench 基准测试的各种任务中展示了最先进的性能。