Information Theoretic Active Exploration in Signed Distance Fields

This paper focuses on exploration and occupancy mapping of unknown environments using a mobile robot. While a truncated signed distance field (TSDF) is a popular, efficient, and highly accurate representation of occupancy, few works have considered optimizing robot sensing trajectories for autonomous TSDF mapping. We propose an efficient approach for maintaining TSDF uncertainty and predicting its evolution from potential future sensor measurements without actually receiving them. Efficient uncertainty prediction is critical for long-horizon optimization of potential sensing trajectories. We develop a deterministic tree-search algorithm that evaluates the information gain between the TSDF distribution and potential observations along sequences of robot motion primitives. Efficient planning is achieved by branch-and-bound pruning of uninformative sensing trajectories. The effectiveness of our active TSDF mapping approach is evaluated in several simulated environments with complex visibility constraints.

Authors

• Kelsey Saulnier
• Nikolay Atanasov 0001
• George J. Pappas
• Vijay Kumar 0001

Keywords

• Robot sensing systems
• Trajectory
• Measurement uncertainty
• Standards
• Uncertainty
• Information Theory
• Signed Distance Function
• Simulation Environment
• Information Gain
• Tree Search
• Unknown Environment
• Motion Primitives
• Frontier
• Free Space
• Angular Velocity
• Mutual Information
• Kalman Filter
• Assumption Of Independence
• Depth Camera
• Linear Velocity
• Depth Measurements
• Object Surface
• Gaussian Variables
• Maps Of Cells
• Gaussian Random Variables
• Occupancy Grid
• Planning Horizon
• 2D Environment
• Gaussian Prior Distribution