Mobile Robot Navigation for Moving Obstacles with Unpredictable Direction Changes, Including Humans

Zeng, Lingqi; Bone, Gary M.

doi:10.1080/01691864.2012.703166

Cited by 9 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, their practical applications were mostly limited to the spectrum of low dimensions. When the number of dimension increases to five or more, the cell-decomposition methods suffer from the "curse of dimensionality" due to the large number of cells, and the potential field methods suffer from the problem of local minima [4] [5]. In early nineties, randomization was proposed in order to solve the problems of local minima (where a local minimum is escaped by a random shift away from it, and a search for a new minimum is initiated) but it would require extensive computational effort in applications of high dimension [6].…”

Section: Related Workmentioning

confidence: 99%

Probabilistic roadmap with self-learning for path planning of a mobile robot in a dynamic and unstructured environment

Zhang

Fattahi

2013

2013 IEEE International Conference on Mechatronics and Automation

View full text Add to dashboard Cite

This paper presents a new path planning method for a mobile robot in an unstructured and dynamic environment. The method consists of two steps: first, a probabilistic roadmap (PRM) is constructed and stored as a graph whose nodes correspond to a collision-free world state for the robot; second, Q-learning-a method of reinforcement learning, is integrated with PRM to determine a proper path to reach the goal. In this manner, the robot is able to use past experience to improve its performance in avoiding not only static obstacles but also moving obstacles, without knowing the nature of the movements of the obstacles. The developed approach is applied to a simulated robot system. The results show that the hybrid PRM-Q path planner is able to converge to the right path successfully and rapidly.

show abstract

Section: Related Workmentioning

confidence: 99%

Probabilistic roadmap with self-learning for path planning of a mobile robot in a dynamic and unstructured environment

Zhang

Fattahi

2013

2013 IEEE International Conference on Mechatronics and Automation

View full text Add to dashboard Cite

show abstract

“…To consider the joint-space velocity limitations, the downscaling scheme discussed in section 4.4 should be conducted. The downscaling factor that represents how much the original maximum velocity should be reduced is calculated using (17).…”

Section: Simulation Examplementioning

confidence: 99%

A Practical Joint-Space Trajectory Generation Method Based on Convolution in Real-Time Control

Yang

Delgado

Choi

2016

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

This paper proposes a joint-space trajectory generation method for practical navigation with a high curvature path of mobile robots. A technique to generate central velocity commands using a convolution operator that considers only the physical limits of a mobile robot was discussed. In practical application, controlling the heading angles along a curved path is required and the existence of obstacles is inevitable. First, we suggested an algorithm that generates a trajectory to consider the heading angles along a smooth Bezier curve by redefinition of the curve parameter. However, the presence of an obstacle along the planned path requires redirection to a new path where geometrical limitations such as high curvature turning points exist, resulting in tracking error. We propose a method that manages a variation of linear interpolation to generate a feasible trajectory while conserving the high curvature path and the merits of convolution. Joint-space trajectories are produced by scaling down the generated central velocity through reduction of the given maximum velocity limit. We show through a simulation example that the proposed method is able to generate a trajectory that can accurately track a planned path on a designed platform based on actual parameters. Finally, an experiment is successfully conducted on a two-wheeled mobile robot, Tetra DS-III, in a real-time control system. The experiment results display distinct advantages in the criteria of time optimality and periodicity of control tasks, while conserving all possible limitations that could occur during navigation compared with previous studies.

show abstract

“…In many service applications, mobile robots need to share their working regions with obstacles including humans. Avoiding collisions with humans and obstacles is a fundamental requirement for these robots [9]. Scenario digitalization or reconstruction is critical in 3D world structure, object localization, mobile robot navigation, and mapping and tracking tasks [10].…”

Section: Introductionmentioning

confidence: 99%

Control system design and study for an automatic mobile robot

Song

Xiao

2015

2015 IEEE International Conference on Information and Automation

View full text Add to dashboard Cite

This paper designs a control system for an automatic handling mobile robot based on s3c2440, which can recognize environment by a laser sensor. And according to the fact that the accumulative error will increase with time in inertial navigation system and steering control is easy to be out of control for heavy robot using differential steering mechanism, two effective solutions are proposed. An inertial navigation algorithm is used for the automatic control of the robot, and an active trap system, including the generation device of magnetic field and detecting device, is designed for eliminating accumulative error. In order to improve steering control precision, a motion control algorithm is presented based on gyroscope and accelerometer. The results of experiments prove the validity of the presented control algorithm, and the navigation performance is improved.

show abstract

Mobile Robot Navigation for Moving Obstacles with Unpredictable Direction Changes, Including Humans

Cited by 9 publications

References 37 publications

Probabilistic roadmap with self-learning for path planning of a mobile robot in a dynamic and unstructured environment

Probabilistic roadmap with self-learning for path planning of a mobile robot in a dynamic and unstructured environment

A Practical Joint-Space Trajectory Generation Method Based on Convolution in Real-Time Control

Control system design and study for an automatic mobile robot

Contact Info

Product

Resources

About