Reactive Control for Collision Evasion with Extended Obstacles

Kim, Jonghoek

doi:10.3390/s22155478

Cited by 2 publications

(3 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The DWA algorithm must account for the impact of the machine fish body’s size. The size of the machine fish is known, and to prevent collisions with obstacles, the expansion coefficient (Kim, 2022) is established at 1.2, expanding the obstacle by 1.2 times its original size.…”

Section: Simulation Experiments Verificationmentioning

confidence: 99%

Path planning for robotic fish based on improved RRT* algorithm and dynamic window approach

Fu,

Chen,

et al. 2024

View full text Add to dashboard Cite

Purpose The purpose of this paper is to address two major challenges faced by robotic fish when operating in underwater environments: insufficient path planning capabilities and difficulties in avoiding dynamic obstacles. To achieve this, a method is proposed that combines the Improved Rapid Randomized Tree Star (IRRT*) with the dynamic window approach (DWA). Design/methodology/approach The RRT-connect algorithm is used to determine an initial feasible path quickly. The quality of sampling points is then improved by dividing the regions and selecting each region’s probability based on its fitness value. The fitness function and roulette wheel method are introduced for region selection. Subtarget points of the DWA algorithm are extracted from the IRRT* algorithm to achieve real-time dynamic path planning. Findings In various maps, the iteration count for the IRRT* algorithm decreased by 61%, 35% and 51% respectively, compared to the RRT* algorithm, whereas the iteration time was reduced by 75%, 34% and 57%, respectively. In addition, the IRRT*-DWA algorithm can successfully navigate through multiple dynamic obstacles, and the average time, path length, etc. do not change much when parameters change, and the stability is high. Originality/value A novel IRRT*-DWA algorithm is proposed, which, by refining the sampling strategy and updating sub-target points in real time, not only addresses the limitations of existing algorithms in terms of path planning efficiency in complex environments but also enhances their capability to avoid dynamic obstacles. Ultimately, experimental results indicate a high level of similarity between the actual and ideal paths.

show abstract

Section: Simulation Experiments Verificationmentioning

confidence: 99%

Path planning for robotic fish based on improved RRT* algorithm and dynamic window approach

Fu,

Chen,

et al. 2024

View full text Add to dashboard Cite

show abstract

“…APF is generated by the addition of the attraction potential field (generated by the goal) and the repulsive potential field (generated by obstacles). Velocity Obstacle (VO) methods can be utilized for collision evasion with moving obstacles [ 22 , 24 , 28 , 29 , 30 , 31 ]. References [ 31 , 32 , 33 ] considered collision avoidance in three-dimensional environments.…”

Section: Introductionmentioning

confidence: 99%

“…Velocity Obstacle (VO) methods can be utilized for collision evasion with moving obstacles [ 22 , 24 , 28 , 29 , 30 , 31 ]. References [ 31 , 32 , 33 ] considered collision avoidance in three-dimensional environments.…”

Section: Introductionmentioning

confidence: 99%

Camera-Based Net Avoidance Controls of Underwater Robots

Kim

2024

Sensors

Self Cite

View full text Add to dashboard Cite

Fishing nets are dangerous obstacles for an underwater robot whose aim is to reach a goal in unknown underwater environments. This paper proposes how to make the robot reach its goal, while avoiding fishing nets that are detected using the robot’s camera sensors. For the detection of underwater nets based on camera measurements of the robot, we can use deep neural networks. Passive camera sensors do not provide the distance information between the robot and a net. Camera sensors only provide the bearing angle of a net, with respect to the robot’s camera pose. There may be trailing wires that extend from a net, and the wires can entangle the robot before the robot detects the net. Moreover, light, viewpoint, and sea floor condition can decrease the net detection probability in practice. Therefore, whenever a net is detected by the robot’s camera, we make the robot avoid the detected net by moving away from the net abruptly. For moving away from the net, the robot uses the bounding box for the detected net in the camera image. After the robot moves backward for a certain distance, the robot makes a large circular turn to approach the goal, while avoiding the net. A large circular turn is used, since moving close to a net is too dangerous for the robot. As far as we know, our paper is unique in addressing reactive control laws for approaching the goal, while avoiding fishing nets detected using camera sensors. The effectiveness of the proposed net avoidance controls is verified using simulations.

show abstract

Reactive Control for Collision Evasion with Extended Obstacles

Cited by 2 publications

References 40 publications

Path planning for robotic fish based on improved RRT* algorithm and dynamic window approach

Path planning for robotic fish based on improved RRT* algorithm and dynamic window approach

Camera-Based Net Avoidance Controls of Underwater Robots

Contact Info

Product

Resources

About