Tham khảo tài liệu 'field and service robotics- recent advances - yuta s. et al (eds) part 3', kỹ thuật - công nghệ, cơ khí - chế tạo máy phục vụ nhu cầu học tập, nghiên cứu và làm việc hiệu quả | Landmark-Based Nonholonomic Visual Homing Kane Usher1 2 Peter Corke1 and Peter Ridley2 1 CSIRO Manufacturing and Infrastructure Technology . Box 883 Kenmore 4069 Queensland Australia firstname . surname @ http cmst automation 2 School of Mechanical Manufacturing and Medical Engineering Queensland University of Technology Brisbane 4001 Queensland Australia Abstract. In this paper we present a method which allows pose stabilization of a car-like vehicle to a learnt location based on feature bearing angle and range discrepancies between the vehicle s current view of the environment and that at the learnt location. We then extend the technique to include obstacle avoidance. Simulations and experimental results using our outdoor mobile platform are presented. 1 Introduction In order to perform useful tasks a mobile robot requires the ability to servo to particular poses in the environment. For the nonholonomic car-like vehicle used in these experiments Brockett 2 showed that there is no smooth continuous feedback control law which can locally stabilise such systems. Insects in general display amazing navigation abilities traversing distances far surpassing the best of our mobile robots on a relative scale. Evolution has provided insects with many shortcuts enabling the achievement of relatively complex tasks with a minimum of resources in terms of processing power and sensors 12 . The high ground temperatures encountered by the desert ant cataglyphis bicolor eliminates pheromones as a potential navigation aid as is used by ants in cooler climates 6 . The desert ant navigates using a combination of path integration and visual homing. Visual homing is the process of matching an agent s current view of a location in a distinctive locale to a pre-stored view at some target position. Discrepancies between the two views are used to generate a command that drives the agent closer to the target position. The process enables the agent to find .
