BIONAV: Bio-inspired Indoor Robot Navigation
PIs: Prof. Dr. Stefan Wermter, Dr. Cornelius Weber
Associates: Xiaomao Zhou
||Robot navigation is the core technology and also a difficult task related to robot perception, planning, implementation and many other aspects in mobile robot research. Different from probabilistic approaches which are mainly based on Kalman or Particle Filters, bio-inspired robot navigation is inspired by navigation behavior in animals and makes hypotheses about how the navigation skills are acquired and implemented in an animal's brain and body. Thus it is a promising direction to mimic animal behavior and attempt to achieve their learning ability for intelligent robots.
Head-direction cells, place cells and grid cells have been found to play a fundamental role in rat navigation and have been computationally modeled. This project aims to develop a navigation system which is based on these biological findings for a real Jackal robot platform. Essentially, robot navigation requires the capabilities of localization, map building, path planning and obstacle avoidance. Moreover, the use of the robot's own cameras and odometry as the only sensor readings can significantly simplify the system.
Thus, the BIONAV project has the following main objectives:
- Construct the appropriate representation of the environment using only visual input. Besides, the map should contain spatial and orientational information for path planning.
- Dependent on the navigation task, dynamically choose a strategy to navigate to the target state.
- Detect obstacles passively and adapt the map-based navigation strategy accordingly.