LEARNING OBSTACLE BEHAVIOR FOR IMPROVED THREAT MAPPING DURING NAVIGATION

visually impaired;obstacle avoidance;collision avoidance;multi agent;threat map;Robotics

Saluja, Kunal

Johns Hopkins University

关键词: visually impaired;    obstacle avoidance;    collision avoidance;    multi agent;    threat map;    Robotics;   

Others  :  https://jscholarship.library.jhu.edu/bitstream/handle/1774.2/39489/SALUJA-THESIS-2016.pdf?sequence=1&isAllowed=y

瑞士|英语

来源: JOHNS HOPKINS DSpace Repository

【 摘 要 】

A novel obstacle evaluation system for the visually impaired is proposed and evaluated inthis thesis. This system assesses the threat in the environment posed by various kinds ofstationary and moving obstacles. It evaluates the behaviors of different classes ofobstacles and learns features based on their collision avoidance strategies. For thepurpose of crowd simulation, Reciprocal Collision Avoidance strategy has been usedhere. This idea can further be generalized to any multi-agent environment and can serveas the building block for new obstacle avoidance algorithms.