Non-prehensile pushing actions have the potential to singulate a target object from its surrounding clutter in order to facilitate the robotic grasping of the target. To address this problem we utilize a heuristic rule that moves the target object towards the workspace's empty space and demonstrate that this simple heuristic rule achieves singulation. We incorporate this effective heuristic rule to the reward in order to train more efficiently reinforcement learning (RL) agents for singulation. Simulation experiments demonstrate that this insight increases performance. Finally, our results show that the RL-based policy implicitly learns something similar to one of the used heuristics in terms of decision making. Qualitative results, code, pre-trained models and simulation environments are available at https://github.com/robot-clutter/improved_rl.
翻译:非致命推力行动有可能将目标对象从周围的杂乱中单挑出来,以便于机器人掌握目标。 为了解决这一问题,我们使用了一种将目标对象移动到工作空间空空空间的超自然规则, 并表明这种简单的超自然规则可以实现单星。 我们将这种有效的超自然规则纳入奖励中, 以便更有效地培训强化学习(RL) 代理器以进行模拟实验。 模拟实验表明, 这种洞察力会提高性能。 最后, 我们的结果显示, 以RL为基础的政策在决策方面隐含地学到了类似于一个用过的超自然学的东西。 定性结果、 代码、 预先训练的模型和模拟环境可在 https://gitub.com/robot- clutter/imprived_rl 上查阅。