Physics-informed Neural Time Fields for Prehensile Object Manipulation

TL;DR

This paper introduces a physics-informed neural network that efficiently learns object manipulation trajectories in cluttered environments without expert data, improving planning speed and success rates for robotic manipulation tasks.

Contribution

A novel multimodal physics-informed neural network that solves the Eikonal equation for object manipulation without expert demonstrations, enabling fast and effective planning in complex scenarios.

Findings

Effective in simulation and real-world tests

Faster training compared to previous methods

High success rates in cluttered environments

Abstract

Object manipulation skills are necessary for robots operating in various daily-life scenarios, ranging from warehouses to hospitals. They allow the robots to manipulate the given object to their desired arrangement in the cluttered environment. The existing approaches to solving object manipulations are either inefficient sampling based techniques, require expert demonstrations, or learn by trial and error, making them less ideal for practical scenarios. In this paper, we propose a novel, multimodal physics-informed neural network (PINN) for solving object manipulation tasks. Our approach efficiently learns to solve the Eikonal equation without expert data and finds object manipulation trajectories fast in complex, cluttered environments. Our method is multimodal as it also reactively replans the robot's grasps during manipulation to achieve the desired object poses. We demonstrate our approach in both simulation and real-world scenarios and compare it against state-of-the-art baseline methods. The results indicate that our approach is effective across various objects, has efficient training compared to previous learning-based methods, and demonstrates high performance in planning time, trajectory length, and success rates. Our demonstration videos can be found at https://youtu.be/FaQLkTV9knI.