End-to-end deep learning-based framework for path planning and collision checking: bin picking application

TL;DR

This paper introduces PPCNet, an end-to-end deep learning framework for real-time path planning and collision checking in robotic systems, significantly reducing planning time while maintaining success rates.

Contribution

The novel PPCNet framework combines two neural networks trained via imitation learning to efficiently generate collision-free paths in complex environments.

Findings

Reduces planning time significantly compared to traditional methods

Achieves comparable success rates and path lengths

Validated in simulation and real-world bin-picking task

Abstract

Real-time and efficient path planning is critical for all robotic systems. In particular, it is of greater importance for industrial robots since the overall planning and execution time directly impact the cycle time and automation economics in production lines. While the problem may not be complex in static environments, classical approaches are inefficient in high-dimensional environments in terms of planning time and optimality. Collision checking poses another challenge in obtaining a real-time solution for path planning in complex environments. To address these issues, we propose an end-to-end learning-based framework viz., Path Planning and Collision checking Network (PPCNet). The PPCNet generates the path by computing waypoints sequentially using two networks: the first network generates a waypoint, and the second one determines whether the waypoint is on a collision-free segment of the path. The end-to-end training process is based on imitation learning that uses data aggregation from the experience of an expert planner to train the two networks, simultaneously. We utilize two approaches for training a network that efficiently approximates the exact geometrical collision checking function. Finally, the PPCNet is evaluated in two different simulation environments and a practical implementation on a robotic arm for a bin-picking application. Compared to the state-of-the-art path planning methods, our results show significant improvement in performance by greatly reducing the planning time with comparable success rates and path lengths.