Learning Task-Oriented Grasping for Tool Manipulation from Simulated Self-Supervision
This addresses the challenge of enabling robots to perform specific tasks with tools, though it is incremental as it builds on existing grasping methods with task-specific constraints.
The paper tackles the problem of task-oriented grasping for tool manipulation in robots by proposing TOG-Net, which jointly optimizes grasping and manipulation policies, achieving task success rates of 71.1% for sweeping and 80.0% for hammering.
Tool manipulation is vital for facilitating robots to complete challenging task goals. It requires reasoning about the desired effect of the task and thus properly grasping and manipulating the tool to achieve the task. Task-agnostic grasping optimizes for grasp robustness while ignoring crucial task-specific constraints. In this paper, we propose the Task-Oriented Grasping Network (TOG-Net) to jointly optimize both task-oriented grasping of a tool and the manipulation policy for that tool. The training process of the model is based on large-scale simulated self-supervision with procedurally generated tool objects. We perform both simulated and real-world experiments on two tool-based manipulation tasks: sweeping and hammering. Our model achieves overall 71.1% task success rate for sweeping and 80.0% task success rate for hammering. Supplementary material is available at: bit.ly/task-oriented-grasp