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.

In this paper, a decoupled offline path planning approach for determining the collision-free path of end effectors of multiple robots involved in coordinated manipulation is proposed. The proposed approach for decoupled path planning is a two-phase approach in which the path for coordinated manipulation is generated with a coupled interaction between collision checking and path planning techniques. Collision checking is done by modelling the links and environment of robot using swept sphere volume technique and utilizing minimum distance heuristic for interference check. While determining the path of the end effector of robots involved in coordinated manipulation, the obstacles present in the workspace are considered as static obstacles and the links of the robots are viewed as dynamic obstacles by the other robot. Coordination is done in offline mode by implementing replanning strategy which adopts incremental A* algorithm for searching the collision-free path. The effectiveness of proposed decoupled approach is demonstrated by considering two examples having multiple six degrees of freedom robots operating in 3D work cell environment with certain static obstacles.