In human-robot coexisting environment, both safety and efficiency are important. Generally, there is a trade-off between them and it is very difficult to strike a good balance between them. We are tackling this problem as follows.
Identification of Types of Obstacles for Mobile Robots
For service robots coexisting with humans, both safety and working efficiency are very important. In order for robots to avoid collisions with surrounding obstacles, the robots must recognize obstacles around them. We classified obstacles into three types, such as stationary, movable, and moving. Also we propose a method to identify the type of obstacles. The experiments were conducted to evaluate the usefulness of the method.
Yusuke Tamura, Yu Murai, Hiroki Murakami, and Hajime Asama: Identification of Types of Obstacles for Mobile Robots, Intelligent Service Robotics, Vol.4, No.2, pp.99-105, 2011. [Springer]
Yusuke Tamura, Yu Murai, Hiroki Murakami and Hajime Asama: Identification of Types of Obstacles and Obstacle Map Building for Mobile Robots, Proceedings of the 6th International Conference on Ubiquitous Robots and Ambient Intelligence, pp.340-344, Gwangju, Korea, October 2009.
Prediction of Pedestrian’s Movement Considering Environmental Information
To plan robots’ motion that achieves a balance between safety and efficiency, it is necessary for mobile robots to predict a risk of collision with humans. In this study, we proposed a method for prediction of pedestrians based on the environmental information.
Shunsuke Hamasaki, Yusuke Tamura, Atsushi Yamashita and Hajime Asama: Prediction of Human’s Movement for Collision Avoidance of Mobile Robot, Proceedings of the IEEE International Conference on Robotics and Biomimetics, pp.1633-1638, Phuket, Thailand, December 2011. [IEEE Xplore]
Pedestrian Behavior Model for Collision Avoidance of Mobile Robots
Human behaviors are inevitably affected by the environment including robots and other objects. In this study, we proposed a pedestrian behavior model considering its intention and a robot control method to avoid collisions based on the estimation of pedestrians’ intention.
Yusuke Tamura, Yoshitaka Terada, Atsushi Yamashita and Hajime Asama: Modelling Behaviour Patterns of Pedestrians for Mobile Robot Trajectory Generation, International Journal of Advanced Robotic Systems, Vol.10, 310, pp.1-11, 2013. [InTech]
Yusuke Tamura, Phuoc Dai Le, Kentarou Hitomi, Naiwala P. Chandrasiri, Takashi Bando, Atsushi Yamashita and Hajime Asama: Development of Pedestrian Behavior Model Taking Account of Intention, Proceedings of the 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp.382-387, Vilamoura, Portugal, October 2012.[IEEE Xplore]
Yusuke Tamura, Tomohiro Fukuzawa and Hajime Asama: Smooth Collision Avoidance in Human-Robot Coexisting Environment, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pp.3887-3892, Taipei, Taiwan, October 2010. [IEEE Xplore]