Autonomous Navigation in Unknown Environments using Sparse Kernel-based Occupancy Mapping
This addresses the problem of safe and efficient autonomous navigation for robots in unknown settings, representing an incremental improvement with a novel mapping method.
The paper tackles real-time occupancy mapping and collision checking for autonomous robots in unknown environments by introducing a sparse kernel-based map representation, achieving effective navigation for an Ackermann-drive robot.
This paper focuses on real-time occupancy mapping and collision checking onboard an autonomous robot navigating in an unknown environment. We propose a new map representation, in which occupied and free space are separated by the decision boundary of a kernel perceptron classifier. We develop an online training algorithm that maintains a very sparse set of support vectors to represent obstacle boundaries in configuration space. We also derive conditions that allow complete (without sampling) collision-checking for piecewise-linear and piecewise-polynomial robot trajectories. We demonstrate the effectiveness of our mapping and collision checking algorithms for autonomous navigation of an Ackermann-drive robot in unknown environments.