|
Experiment of Robust Driving Assistance Control for Skid Steer Welfare Vehicle using Model Error Compensator |
|
Tomoki Tanaka, Hirotaka Miyamoto, Hiroshi Okajima, Nobutomo Matsunaga(Kumamoto University, Japan) |
| Recently, welfare vehicles are widely used by patients and elders indoors.
In order to expand driving area for welfare vehicles, the skid steer mechanism is focused on. However, the skid steer vehicle(SSV) has disadvantage that the maneuvering assistance is required because its steering is highly affected by road condition.
This study aims to propose driving assistance controller consists of Model Error Compensator (MEC), Extended Kalman Filter (EKF) and estimation of cornering power of SSV. The effectiveness of the proposed control system is confirmed by the outdoor driving experiment. |
|
|
Motion Control of a Powered Wheelchair using a Gazing Feature in an Environment |
|
Airi Ishizuka, Ayanori Yorozu, Masaki Takahashi(Keio University, Japan) |
| This paper describes the motion control system for a powered wheelchair using a gaze in an unknown environment. Recently, new Human-Computer Interfaces (HCIs) that have replaced joysticks have been developed for a person with a disability of the upper body. In this paper, movement of the eyes is used as an HCI. The wheelchair control system proposed in this study aims to achieve an operation such that a passenger gazes towards the direction he or she wants to move in the unknown environment. The effectiveness of the proposed system is demonstrated through experiments in a real environment. |
|
|
Path Smoothing Extension for Various Robot Path Planners |
|
Abhijeet Ravankar, Ankit A Ravankar, Yukinori Kobayashi, Takanori Emaru(Hokkaido University, Japan) |
| We present a novel path smoothing extension which uses the geometry of hypocycloids to smooth out the sharp and angular turns of the robot's path and generates a smooth path for the robot to traverse. The proposed technique works as an `extension' and can be used in conjunction with any of the previously proposed global path planners. The proposed extension also generates `nodes' on the robot's path which can be used as points of retreat for the robot to avoid collision with other robots. We discuss the results in both simulated and real environment. |
|
|
Robot Collaboration in Warehouse |
|
Nantawat Pinkam, Francois Bonnet, Nak Young Chong(Japan Advanced Institute of Science and Technology, Japan) |
| In this work, the problem consists of a transportation of multiple items to stations that make request using multi-robot systems with restriction on the limit carrying capacity in a simulated environment. We compare two collection strategies, namely the individual collection method that let each robot takes responsibility for its own station and the collaborative collection method with local search that allows robots take nearest items and deliver them to all stations. By comparing these two methods, collaborative method is able to reduce the traveling cost up to 15.4% from individual method. |
|
|
Generation of Locally Optimal Trajectory against Moving Obstacles using Gaussian Sampling |
|
Jaehyeon Park, H. Jin Kim(Seoul National University, Korea) |
| This paper presents a trajectory generation algorim with input optimization in receding horizon setting by combining episode-based reinforcement learning. This algorithm finds the locally optimal trajectory of current situation by applying Gaussian sampling to existing policy. This locally optimal trajectory formed as receding horizon is used for step-by-step decision making. After one episode ends, the entire trajectory data is used for reinforcement learning to improve global control policy of generating trajectory. Therefore performance of the trajectory can be improved along the episodes. |
|
|
Path planning for autonomous mobile robots with mobility and threat information |
|
Hee-beom Lee, H. Jin Kim(Seoul National University, Korea) |
| For successful autonomous navigation, safety and mobility should be considered for path planning. This path can be obtained by applying the threat and mobility information to calculate the cost of path planning. In this paper we consider the case where threat property is provided as an indirect form of information which requires processing to represent in the cost function. Thus, we should generate the threat map from the threat information for path planning. From the path planning results, we confirmed that generated path satisfies the safety and mobility. |
|