Abstract
For an autonomous robot to move safely in an environment where people are around and moving dynamically without knowing their goal position, it is required to set navigation rules and human behaviors. This problem is challenging with the highly stochastic behavior of people. Previous methods believe to provide features of human behavior, but these features vary from person to person. The method focuses on setting social norms that are telling the robot what not to do. With deep reinforcement learning, it has become possible to set a time-efficient navigation scheme that regulates social norms. The solution enables mobile robot full autonomy along with collision avoidance in people rich environment.
Highlights
Autonomous Navigation in a highly stochastic environment is bound to uncertainty with the prediction of future behavior in a multi-agent system
This paper deals with a strong foundation of mapping, localization, and path planning with a deep reinforcement learning method having multiple agents (Kim et al, 2014)
This paper presents the implementation of Autonomous Navigation using deep reinforcement learning in a ROS framework
Summary
Autonomous Navigation in a highly stochastic environment is bound to uncertainty with the prediction of future behavior in a multi-agent system. Sensor fusion is again a challenging task that involves the coupling of different sensors for object detection and smooth movement of the robot (Bai et al, 2015). This paper deals with a strong foundation of mapping, localization, and path planning with a deep reinforcement learning method having multiple agents (Kim et al, 2014). Autonomous navigation problem having a set of challenges which includes an ever-changing environment, prediction of people’s behavior while moving, avoiding obstacles, etc. While predicting people’s behavior, it is essential to bound the scope with simple kinematics and impose rules for avoiding collision amongst the agents (Helbing et al, 1995)
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call