First Plan Then Evaluate: Multi-Target Planning with Post-Planning Success Evaluation Improves Learning-Based Grasping Pipelines
For robotic manipulation, this work improves the efficiency and success rate of grasping pipelines by reordering planning and evaluation, offering a practical improvement over existing frameworks.
The paper addresses the inefficiency of the generator-evaluator-planner framework for multi-finger grasping, where time is wasted on trajectory optimization for low-ranked grasps or accuracy is sacrificed. The proposed method plans trajectories to multiple grasp targets first, then evaluates success likelihood at the terminal configuration, improving grasp success rate and reducing planning time across various objects, generators, and planners, with real-world generalization.
Autonomous multi-finger grasping is a fundamental capability in robotic manipulation. Optimization-based approaches show strong performance, but tend to be sensitive to initialization and are potentially time-consuming. As an alternative, the generator-evaluator-planner framework has been proposed. A generator generates grasp candidates, an evaluator ranks the proposed grasps, and a motion planner plans a trajectory to the highest-ranked grasp. If the planner doesn't find a trajectory, a new trajectory optimization is started with the next-best grasp as the target and so on. However, executing lower-ranked grasps means a lower chance of grasp success, and multiple trajectory optimizations are time-consuming. Alternatively, relaxing the threshold for motion planning accuracy allows for easier computation of a successful trajectory but implies lower accuracy in estimating grasp success likelihood. It's a lose-lose proposition: either spend more time finding a successful trajectory or have a worse estimate of grasp success. We propose a framework that plans trajectories to a set of generated grasp targets, the evaluator estimates the grasp success likelihood at the terminal configuration of the planned trajectories, and the robot executes the trajectory most likely to succeed. Our experiments show our approach improves over the traditional generator-evaluator-planner framework across different objects, generators, and motion planners, and successfully generalizes to novel environments in the real world, including different shelves and table heights. Project Website: https://martinmatak.github.io/fpte/