Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Understanding visual attention beehind bee-inspired UAV navigation

Pranav Rajbhandari, Abhi Veda, Matthew Garratt, Mandyam Srinivasan, Sridhar Ravi

Abstract

Bio-inspired design is often used in autonomous UAV navigation due to the capacity of biological systems for flight and obstacle avoidance despite limited sensory and computational capabilities. In particular, honeybees mainly use the sensory input of optic flow, the apparent motion of objects in their visual field, to navigate cluttered environments. In our work, we train a Reinforcement Learning agent to navigate a tunnel with obstacles using only optic flow as sensory input. We inspect the attention patterns of trained agents to determine the regions of optic flow on which they primarily base their motor decisions. We find that agents trained in this way pay most attention to regions of discontinuity in optic flow, as well as regions with large optic flow magnitude. The trained agents appear to navigate a cluttered tunnel by avoiding the obstacles that produce large optic flow, while maintaining a centered position in their environment, which resembles the behavior seen in flying insects. This pattern persists across independently trained agents, which suggests that this could be a good strategy for developing a simple explicit control law for physical UAVs.

Understanding visual attention beehind bee-inspired UAV navigation

Abstract

Bio-inspired design is often used in autonomous UAV navigation due to the capacity of biological systems for flight and obstacle avoidance despite limited sensory and computational capabilities. In particular, honeybees mainly use the sensory input of optic flow, the apparent motion of objects in their visual field, to navigate cluttered environments. In our work, we train a Reinforcement Learning agent to navigate a tunnel with obstacles using only optic flow as sensory input. We inspect the attention patterns of trained agents to determine the regions of optic flow on which they primarily base their motor decisions. We find that agents trained in this way pay most attention to regions of discontinuity in optic flow, as well as regions with large optic flow magnitude. The trained agents appear to navigate a cluttered tunnel by avoiding the obstacles that produce large optic flow, while maintaining a centered position in their environment, which resembles the behavior seen in flying insects. This pattern persists across independently trained agents, which suggests that this could be a good strategy for developing a simple explicit control law for physical UAVs.

Paper Structure

This paper contains 15 sections, 1 equation, 5 figures.

Table of Contents

  1. Introduction
  2. Bio-inspired autonomous navigation
  3. Reinforcement Learning
  4. Explainable AI/Shapley Values
  5. Previous Work
  6. Buggy robotics
  7. Explainable navigation
  8. Simulation Environment
  9. Observation Space
  10. Action Space
  11. Reward Function/Termination
  12. Agent Policy
  13. Results
  14. Discussion
  15. Conclusion and Future Work

Figures (5)

  • Figure 1: Screenshot of the AirSim simulation environment
  • Figure 2: Policy Network Architecture. Yellow boxes represent transitions with learnable weights.
  • Figure 3: The attention pattern of trained agents flying through a tunnel, averaged over four independently trained agents.
  • Figure 4: Trajectories from a trained agent flying through different tunnels: (a) Easier tunnel with two obstacles placed off-center, (b) Difficult tunnel with three obstacles, one placed centrally and two placed off-center.
  • Figure 5: Comparison of attention patterns for four independently trained agents. The average attention is largest at nearby obstacle edges; this pattern exists in each of the four agent policy networks as well.