Person following with obstacle avoidance based on multi-layered mean shift and force field method

2010 ◽  
Author(s):  
Woo-han Yun ◽  
Dohyung Kim ◽  
Jaeyeon Lee
Keyword(s):  
Force Field ◽  
Obstacle Avoidance ◽  
Mean Shift ◽  
Field Method ◽  
Person Following

scholarly journals On the Performance Analyses of a Modified Force Field Algorithm and Neural Network Approach for Obstacle Avoidance in Swarm Robotics

2021 ◽  
Vol 2 (3) ◽  
Author(s):  
Girish Balasubramanian ◽  
Senthil Arumugam Muthukumaraswamy ◽  
Xianwen Kong
Keyword(s):  
Neural Network ◽  
Force Field ◽  
Obstacle Avoidance ◽  
Swarm Robotics ◽  
Field Method ◽  
Network Approach ◽  
Neural Network Approach ◽  
The Neural Network ◽  
Swarm Robots ◽  
Swarm Robot

AbstractObstacle avoidance is a major hurdle when implementing mobile robots and swarm robots. Swarm robots work in groups and therefore require an efficient and functional obstacle avoidance algorithm to stay collision free between themselves and their surroundings. This paper reviews previous research in obstacle avoidance implementation using the force field method (FFM), also known as potential field method (PFM) and a neutral network approach. Moreover, this paper aims to execute simulations using a modified force field algorithm and a neural network approach and compare them. The obtained results are analyzed to identify the performance characteristics and the time taken to perform tasks using a singular mobile robot against a swarm robot environment consisting of four and ten robots, respectively, in both simulation cases. Simulations showed that the algorithm was successful in navigating obstacles for both single and swarm robot environments. A single robot was found to take up to 340% longer to arrive at the required location compared to the first robot in the experiment. Moreover, it was found that the neural network approach showed ~ 27% improvement over the modified force field algorithm when it comes to cases where more than four robots are being used.

Integrated Steering and Braking Control System for Collision Avoidance by Using Virtual Repulsive Force Field Method

2018 ◽  
Author(s):  
Atsushi Yokoyama ◽  
Pongsathorn Raksincharoensak ◽  
Naoto Yoshikawa
Keyword(s):  
Force Field ◽  
Collision Avoidance ◽  
Autonomous Driving ◽  
Field Method ◽  
Repulsive Force ◽  
Driver Assistance Systems ◽  
Mass Model ◽  
Braking Control ◽  
And Control ◽  
Control Activation

Advanced Driver Assistance Systems (ADAS) and autonomous driving systems are being enhanced to deal with various types of collision avoidance use-case scenarios. To handle those complicated scenarios, a unified two-dimensional planar motion control methodology assuming virtual repulsive force from obstacles is introduced, which is physically interpretable and comprehensible. The direction and magnitude of virtual repulsive force are determined considering the orientation of obstacle surface planes and the friction limit between tires and road surface respectively. Applying the concept of virtual repulsive force field, the collision avoidance path can be derived from geometrical relationship and the control activation points can be obtained as algebraic solutions. By using a simple particle mass model, the formulation for path and control activation point is described. The simulation is conducted against not only in the case of a straight roadway but also in the case of a curve roadway. By designing feedforward and feedback controllers based on a two-wheel vehicle dynamics model, the effectiveness of the proposed method is verified and the feasibility of controller implementation for actual vehicle is also investigated.

Sign in / Sign up

Export Citation Format

Share Document