Gpu boosts robot exploration by cutting redundant scanning time
GPU-Accelerated Path-Dependent Marginal Information Gain for Autonomous Exploration
Robotics
Summary
When robots explore unknown areas, they try to pick spots to look around that will give them the most new information. Usually, they assume each new spot is independent, ignoring overlaps with what they've already seen, which can slow things down. The authors present a new method that uses a graphics processor (GPU) to quickly figure out the real extra information each new viewing spot adds along a path, avoiding repeated work. This makes robot exploration faster and more efficient in both tests on computers and real environments.
What this means in practice
- •For robotics engineers: Speed up robot mapping by efficiently identifying new viewpoints with less redundant scanning using gpu-accelerated path-dependent gain.
- •For embedded systems developers: Integrate efficient gpu-based marginal information gain computations on edge hardware for faster autonomous exploration.
Authors
João Félix Mendes, Rodrigo Ventura, Meysam Basiri
Abstract
Autonomous exploration demands that robots continuously evaluate candidate viewpoints based on their expected information gain and execution cost. Sampling-based planners estimate this gain by volumetric raycasting and, due to its computational cost, evaluate candidates under an assumption of mutual independence, ignoring the overlap between viewpoints along the same path. This work presents a GPU-accelerated method for computing path-dependent marginal information gain, where instead of storing and merging the observed unknown voxels along each candidate path, previous observations are represented using depth buffers. Candidate rays are projected into the depth buffers of their ancestors to identify observation overlap and exclude regions expected to be observed. The planning tree is evaluated in depth order to maintain the dependency between viewpoints and their optimized yaws, while candidate nodes and rays at each level are processed in parallel on the GPU. The proposed method stays within 5-10% of the exact marginal gain computed using voxel hash maps, with speed-ups of up to 118x on a desktop GPU and 28x on an NVIDIA Jetson Orin NX. The method was integrated into two sampling-based exploration planners and evaluated in three simulation environments, where marginal gain reduced the time to 95% coverage in five of the six evaluated planner-environment combinations. Real-world experiments also showed a 30% reduction in the time to 95% coverage, as well as earlier exploration termination times.