A collision-free motion planning method by integrating complexity-reduction SLAM and learning-based artificial force design

Liu, Lei; Guo, Rui; Wu, Junan

doi:10.1016/j.robot.2017.10.017

Cited by 8 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to the original repulsive force, the robot will be additionally subjected to the deflection force exerted by the flow field when it is within the action range. Since the direction of the deflection force is perpendicular to the repulsive force, the robot still has an additional force to get rid of the critical region that causes local minima and GNRON issues 26 , while the second innovation is to introduce the PID control theory to adjust the parameters in the compound potential field in real time, so as to better solve the defects of the traditional APF algorithm.…”

Section: Algorithm Designmentioning

confidence: 99%

Obstacle avoidance of mobile robots using modified artificial potential field algorithm based on vortex and PID adjustment

Sheng

Wang²

2022

International Conference on Advanced Sensing and Smart Manufacturing (ASSM 2022)

View full text Add to dashboard Cite

In recent years, autonomous mobile robot has become a key research direction in academia due to their good application prospects. The ability to autonomously avoid obstacles and reach a preset target point is the basic requirement of an intelligent mobile robot. As a common obstacle avoidance algorithm for mobile robots, artificial potential field algorithm (APF) has defects such as local minima problem and GNRON problem. Aiming at the shortcomings of the traditional APF algorithm, this paper proposes an improved artificial potential field algorithm based on point vortex and PID adjustment. The implementation of the improved algorithm is based on the two following main points. Firstly, an irrotational point vortex flow field is added to the original repulsion field of the obstacle to form a composite potential field. Properties of point vortex are used to provide additional virtual deflection force to the robot to avoid getting stuck. Secondly, aiming at GNRON problem, the strength of vortex and the range of action of the vortex repulsive composite potential field are adjusted in real time by means of PID adjustment. Finally, in order to verify the feasibility of the improved algorithm proposed in this paper, a comparison with the traditional APF algorithm was performed in seven environments with different obstacle layouts. The results show that the improved algorithm can be effectively applied to a variety of obstacle environments. Moreover, the local minimal value problem and GNRON problem of the traditional APF algorithm are successfully solved. The mobile robot can flexibly and efficiently avoid obstacles and reach the end point.

show abstract

Section: Algorithm Designmentioning

confidence: 99%

Obstacle avoidance of mobile robots using modified artificial potential field algorithm based on vortex and PID adjustment

Sheng

Wang²

2022

International Conference on Advanced Sensing and Smart Manufacturing (ASSM 2022)

View full text Add to dashboard Cite

show abstract

“…This detection method is based on a novel event-based camera that only responds to local changes in brightness, and can detect edges directly from the camera. The other work is related to Kalman filter vision [18], which has low complexity but can still be overwhelmed by increasing the number of landmarks.…”

Section: Corner Detection and Applicationsmentioning

confidence: 99%

Line–Circle–Square (LCS): A multilayered geometric filter for edge-based detection

Tafrishi

Dai

Kandjani

2021

Robotics and Autonomous Systems

View full text Add to dashboard Cite

This paper presents a state-of-the-art filter that reduces the complexity in object detection, tracking and mapping applications. Existing edge detection and tracking methods are proposed to create suitable autonomy for mobile robots, however, many of them face overconfidence and large computations at the entrance to scenarios with an immense number of landmarks. The method in this work, the Line-Circle-Square (LCS) filter, claims that mobile robots without a large database for object recognition and highly advanced prediction methods can deal with incoming objects that the camera captures in real-time. The proposed filter applies detection, tracking and learning to each defined expert to extract higher level information for judging scenes without over-calculation. The interactive learning feed between each expert increases the consistency of detected landmarks that works against overwhelming detected features in crowded scenes. Our experts are dependent on trust factors' covariance under the geometric definitions to ignore, emerge and compare detected landmarks. The experiment validates the effectiveness of the proposed filter in terms of detection precision and resource usage in both experimental and real-world scenarios.

show abstract

“…This detection method is based on a novel event-based camera that only responds to local changes in brightness, and can detect edges directly from the camera. The other work is related to Kalman filter vision [37], which has low complexity but can still be overwhelmed by increasing the number of landmarks.…”

Section: B Corner Detection and Applicationsmentioning

confidence: 99%

Line-Circle: A Geometric Filter for Single Camera Edge-Based Object Detection

Tafrishi

Kandjani

2017

2017 5th RSI International Conference on Robotics and Mechatronics (ICRoM)

View full text Add to dashboard Cite

This paper presents a state-of-the-art approach in object detection for being applied in future SLAM problems. Although, many SLAM methods are proposed to create suitable autonomy for mobile robots namely ground vehicles, they still face overconfidence and large computations during entrance to immense spaces with many landmarks. In particular, they suffer from impractical applications via sole reliance on the limited sensors like camera. Proposed method claims that unmanned ground vehicles without having huge amount of database for object definition and highly advance prediction parameters can deal with incoming objects during straight motion of camera in real-time. Line-Circle (LC) filter tries to apply detection, tracking and learning to each defined experts to obtain more information for judging scene without over-calculation. In this filter, circle expert let us summarize edges in groups. The Interactive feedback learning between each expert creates minimal error that fights against overwhelming landmark signs in crowded scenes without mapping. Our experts basically are dependent on trust factors' covariance with geometric definitions to ignore, emerge and compare detected landmarks. The experiment for validating the model is taken place utilizing a camera beside an IMU sensor for location estimation.

show abstract

A collision-free motion planning method by integrating complexity-reduction SLAM and learning-based artificial force design

Cited by 8 publications

References 33 publications

Obstacle avoidance of mobile robots using modified artificial potential field algorithm based on vortex and PID adjustment

Obstacle avoidance of mobile robots using modified artificial potential field algorithm based on vortex and PID adjustment

Line–Circle–Square (LCS): A multilayered geometric filter for edge-based detection

Line-Circle: A Geometric Filter for Single Camera Edge-Based Object Detection

Contact Info

Product

Resources

About