DCLP++ improves robot navigation by using footprint clearance
DCLP++: Learning to Navigate with Footprint Clearance and Relative Motion
Robotics
Summary
Robots need to navigate safely among moving obstacles, which is challenging because they must understand their surroundings and how close they are to other objects. The authors developed a method called DCLP++ that measures distances based on the robot's actual shape, or footprint, rather than just the sensor's location. This helps the robot better estimate space and avoid collisions. In tests, their approach improved the success rate of the robot navigating through moving obstacles compared to using sensor-based distances. However, they note that more work is needed to see how well these results transfer to different robot types and motions.
local navigationfootprint clearanceLiDARrelative motiondynamic environmentsEuclidean distancerobot footprintpolicy inputmotion variantssuccess rate
Authors
Shanze Wang, Wei Zhang
Abstract
We present DCLP++, a local navigation frameworkthat uses footprint clearance as the geometric basis for studying relative motion features in dynamic environments. Each valid LiDAR return is mapped to its shortest Euclidean distance from the filled robot footprint before reciprocal encoding, replacing distance from the sensor with distance to the occupied body. Radial measurementsor simulated planar relative velocities provide short-horizon features without static-dynamic labels in the policy input. A preliminary study uses a rectangular robot with a speed limit of 1 m/s among 20 moving obstacles. On 100 fixed validation tasks, two selected training seeds yield mean success rates of 42% with sensor rangeand 70% with footprint clearance after 200,000 environment steps.Motion variants show mixed additional gains. These results supportthe clearance-based observation in the evaluated setting; reliable motion benefits and transfer across robots require further evaluation.