Robot Local Planner: A Periodic Sampling-Based Motion Planner with Minimal Waypoints for Home Environments

TL;DR

Evaluation experiments demonstrated that the RLP outperformed existing methods in terms of motion planning time, motion duration, and robustness, confirming its effectiveness in home environments.

Abstract

The objective of this study is to enable fast and safe manipulation tasks in home environments. Specifically, we aim to develop a system that can recognize its surroundings and identify target objects while in motion, enabling it to plan and execute actions accordingly. We propose a periodic sampling-based whole-body trajectory planning method, called the "Robot Local Planner (RLP)." This method leverages unique features of home environments to enhance computational efficiency, motion optimality, and robustness against recognition and control errors, all while ensuring safety. The RLP minimizes computation time by planning with minimal waypoints and generating safe trajectories. Furthermore, overall motion optimality is improved by periodically executing trajectory planning to select more optimal motions. This approach incorporates inverse kinematics that are robust to base position errors, further enhancing robustness. Evaluation experiments demonstrated that the RLP outperformed existing methods in terms of motion planning time, motion duration, and robustness, confirming its effectiveness in home environments. Moreover, application experiments using a tidy-up task achieved high success rates and short operation times, thereby underscoring its practical feasibility.

Figures (5)

• Figure 1: Trajectory planning of the RLP. Blue squares represent obstacles. Green lines denote straight-line trajectories, orange lines indicate three-point trajectories, and blue lines show previously selected trajectories. Solid lines represent the selected trajectories, which are the shortest collision-free trajectories, while dashed lines indicate unselected trajectories.
• Figure 2: System overview of the RLP. The robot's whole-body trajectory is planned through the processes of trajectories generation, time optimization, evaluation, and validation.
• Figure 3: Experimental system
• Figure 4: Examples of robot trajectories and their environments are shown. D shows an example when robust IK is utilized, showing a tendency to maintain distance from obstacles to avoid collisions due to base position control errors. In contrast, E shows when robust IK is not used. In this case, the robot is closer to obstacles compared to D, resulting in lower robustness.
• Figure 5: Setup and execution of the tidy-up task.