Risk-Aware Path Planning Under Uncertainty in Dynamic Environments

Cai, Kuanqi; Wang, Chaoqun; Song, Shuang; Chen, Haoyao; Meng, Max Q.-H.

doi:10.1007/s10846-021-01323-3

Cited by 21 publications

(10 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…9, 10, and 11 show that, with the increase of distance for the RMB, the time complexity and number of search nodes to find the target decreased, whereas the path cost increased. Therefore, an optimal RMB selection is essential and is performed using the proposed formula in Equations ( 5), (6), and (7), as described in subsection III (C).…”

Section: ) Experimental Results Using Different Sizes (N) Of the Robo...mentioning

confidence: 99%

“…A robot with global path planning needs to know the environmental information partially, such as a map of the environment required to calculate the optimal route from the start position to the goal position. The algorithm partially knew the obstacle map and the effectiveness of these algorithms is evaluated by their ability to find a valid path if one exists [5,6]. In contrast, local path planning requires the robot to search its surroundings using sensors and find a path to reach the goal in an environment with unknown information [5].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Effectiveness of Robot Motion Block on A-Star Algorithm for Robotic Path Planning

Kabir

Watanobe

Naruse

et al. 2022

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

Efficient path planning and minimization of path movement costs for collision-free faster robot movement are very important in the field of robot automation. Several path planning algorithms have been explored to fulfill these requirements. Among them, the A-star (A*) algorithm performs better than others because of its heuristic search guidance. However, the performance, effectiveness, and searching time complexity of this algorithm mostly depends on the robot motion block to search for the goal by avoiding obstacles. With this challenge kept in mind, this paper proposes an efficient robot motion block with different block sizes for the A* path planning algorithm. The proposed approach reduces robots’ path cost and time complexity to find the goal position as well as avoid obstacles. In this proposed approach, grid-based maps are used where the robot’s next move is decided by searching eight directions among the surrounding grid points. However, the proposed robot motion blocks size has a significant effect on path cost and time complexity of the A* path planning algorithm. For the experiment and to validate the efficiency of the proposed approach, an online benchmarked dataset is used. The proposed approach is applied on thousands of different grid maps with various obstacles, starting, and goal positions. The obtained results from the experiment show that the presented robot motion blocks reduce the robot’s pathfinding time complexity and number of search nodes by maintaining a minimum path cost towards the goal position.

show abstract

Section: ) Experimental Results Using Different Sizes (N) Of the Robo...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Effectiveness of Robot Motion Block on A-Star Algorithm for Robotic Path Planning

Kabir

Watanobe

Naruse

et al. 2022

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

show abstract

“…Mapless planners [3][4][5]7] only employ a local map that is just enough for local planning, and a memoryless one [6] plans directly on sensor data. Distinguishing from those, map-based planning systems [8,9] generally integrate global maps [10,11] a priori and a global planning algorithm such as RRT* [12] to guarantee planning completeness in tasks such as exploration, [13][14][15][16][17] or navigating toward a goal [18][19][20]. All mapless and memoryless planners cannot access any map but use sensor data.…”

Section: Introductionmentioning

confidence: 99%

Depth-based Sampling and Steering Constraints for Memoryless Local Planners

Nguyen¹,

Nguyen²,

Choudhury³

et al. 2022

Preprint

View full text Add to dashboard Cite

By utilizing only depth information, the paper introduces a novel but efficient local planning approach that enhances not only computational efficiency but also planning performances for memoryless local planners. The sampling is first proposed to be based on the depth data which can identify and eliminate a specific type of in-collision trajectories in the sampled motion primitive library. More specifically, all the obscured primitives' endpoints are found through querying the depth values and excluded from the sampled set, which can significantly reduce the computational workload required in collision checking. On the other hand, we furthermore propose a steering mechanism also based on the depth information to effectively prevent an autonomous vehicle from getting stuck when facing a large convex obstacle, providing a higher level of autonomy for a planning system. Our steering technique is theoretically proved to be complete in scenarios of convex obstacles. To evaluate effectiveness of the proposed DEpth based both Sampling and Steering (DESS) methods, we implemented them in the synthetic environments where a quadrotor

show abstract

“…Risk-aware planning involves sequential decision-making in dynamic and uncertain environments, where agents must consider the risks associated with their actions and corresponding costs and rewards [6]. Risk-seeking agents are willing to take lower expected reward in exchange for a higher reward variance (more risk), while risk-averse agents are willing to take a lower expected reward in exchange for lower reward variance (less risk).…”

Section: Introductionmentioning

confidence: 99%

Game-Theoretic Planning for Autonomous Driving among Risk-Aware Human Drivers

Chandra¹,

Wang²,

Schwager³

et al. 2022

Preprint

View full text Add to dashboard Cite

We present a novel approach for risk-aware planning with human agents in multi-agent traffic scenarios. Our approach takes into account the wide range of human driver behaviors on the road, from aggressive maneuvers like speeding and overtaking, to conservative traits like driving slowly and conforming to the right-most lane. In our approach, we learn a mapping from a data-driven human driver behavior model called the CMetric to a driver's entropic risk preference. We then use the derived risk preference within a game-theoretic risk-sensitive planner to model risk-aware interactions among human drivers and an autonomous vehicle in various traffic scenarios. We demonstrate our method in a merging scenario, where our results show that the final trajectories obtained from the risk-aware planner generate desirable emergent behaviors. Particularly, our planner recognizes aggressive human drivers and yields to them while maintaining a greater distance from them. In a user study, participants were able to distinguish between aggressive and conservative simulated drivers based on trajectories generated from our risk-sensitive planner. We also observe that aggressive human driving results in more frequent lane-changing in the planner. Finally, we compare the performance of our modified risk-aware planner with existing methods and show that modeling human driver behavior leads to safer navigation.

show abstract

Risk-Aware Path Planning Under Uncertainty in Dynamic Environments

Cited by 21 publications

References 35 publications

Effectiveness of Robot Motion Block on A-Star Algorithm for Robotic Path Planning

Effectiveness of Robot Motion Block on A-Star Algorithm for Robotic Path Planning

Depth-based Sampling and Steering Constraints for Memoryless Local Planners

Game-Theoretic Planning for Autonomous Driving among Risk-Aware Human Drivers

Contact Info

Product

Resources

About