Depth-based Sampling and Steering Constraints for Memoryless Local Planners

TL;DR

This paper presents a depth-based local planning approach that improves computational efficiency and success rates for memoryless planners by using depth data for sampling and steering, especially in cluttered environments.

Contribution

The paper introduces a novel depth-based sampling and steering method (DESS) that reduces collision checking workload and enhances navigation performance in local planners.

Findings

Significantly reduces collision checking workload.

Achieves success rates over 99.6% in simulated cluttered environments.

Decreases computation time while evaluating more trajectories.

Abstract

By utilizing only depth information, the paper introduces a novel but efficient local planning approach that enhances not only computational efficiency but also planning performances for memoryless local planners. The sampling is first proposed to be based on the depth data which can identify and eliminate a specific type of in-collision trajectories in the sampled motion primitive library. More specifically, all the obscured primitives' endpoints are found through querying the depth values and excluded from the sampled set, which can significantly reduce the computational workload required in collision checking. On the other hand, we furthermore propose a steering mechanism also based on the depth information to effectively prevent an autonomous vehicle from getting stuck when facing a large convex obstacle, providing a higher level of autonomy for a planning system. Our steering technique is theoretically proved to be complete in scenarios of convex obstacles. To evaluate effectiveness of the proposed DEpth based both Sampling and Steering (DESS) methods, we implemented them in the synthetic environments where a quadrotor was simulated flying through a cluttered region with multiple size-different obstacles. The obtained results demonstrate that the proposed approach can considerably decrease computing time in local planners, where more trajectories can be evaluated while the best path with much lower cost can be found. More importantly, the success rates calculated by the fact that the robot successfully navigated to the destinations in different testing scenarios are always higher than 99.6% on average.