Parallelized Control-Aware Motion Planning With Learned Controller Proxies

Chow, Scott; Chang, Dongsik; Hollinger, Geoffrey A.

doi:10.1109/lra.2023.3248900

Cited by 4 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To the best of our knowledge, there is very little previous work on parallel kinodynamic planning. All existing approaches are sampling-based and employ a straightforward parallelization to execute the steer operation in batch-either on CPU for steering with boundary value solvers [37] or on the GPU for steering with neural networks in batch [38]. Consequently, they inherit the same limitations as sampling-based planners, where the sampling of states can be nontrivial.…”

Section: Related Workmentioning

confidence: 99%

Interleaving Graph Search and Trajectory Optimization for Aggressive Quadrotor Flight

Natarajan

Choset

Likhachev

2021

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Quadrotors can achieve aggressive flight by tracking complex manuevers and rapidly changing directions. Planning for aggressive flight with trajectory optimization could be incredibly fast, even in higher dimensions, and can account for dynamics of the quadrotor, however, only provides a locally optimal solution. On the other hand, planning with discrete graph search can handle non-convex spaces to guarantee optimality but suffers from exponential complexity with the dimension of search. We introduce a framework for aggressive quadrotor trajectory generation with global reasoning capabilities that combines the best of trajectory optimization and discrete graph search. Specifically, we develop a novel algorithmic framework that interleaves these two methods to complement each other and generate trajectories with provable guarantees on completeness up to discretization. We demonstrate and quantitatively analyze the performance of our algorithm in challenging simulation environments with narrow gaps that create severe attitude constraints and push the dynamic capabilities of the quadrotor. Experiments show the benefits of the proposed algorithmic framework over standalone trajectory optimization and graph search-based planning techniques for aggressive quadrotor flight.

show abstract

Section: Related Workmentioning

confidence: 99%

Interleaving Graph Search and Trajectory Optimization for Aggressive Quadrotor Flight

Natarajan

Choset

Likhachev

2021

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

show abstract

“…Generally, the path planning for autonomous underwater vehicle navigation differs from that of land and presents typical challenges in 3D space [17]. Numerous techniques have been proposed for optimizing 3D paths, including statistical optimization-based strategies, for example, the A-star algorithm [18], potential-based methods [19], ant colony algorithms, and genetic algorithms.…”

Section: Introductionmentioning

confidence: 99%

Underwater Vehicle Path Planning Based on Bidirectional Path and Cached Random Tree Star Algorithm

Gao,

Geng,

Zhang

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Underwater autonomous path planning is a critical component of intelligent underwater vehicle system design, especially for maritime conservation and monitoring missions. Effective path planning for these robots necessitates considering various constraints related to robot kinematics, optimization objectives, and other pertinent factors. Sample-based strategies have successfully tackled this problem, particularly the rapidly exploring random tree star (RRT*) algorithm. However, conventional path-searching algorithms may face challenges in the marine environment due to unique terrain undulations, sparse and unpredictable obstacles, and inconsistent results across multiple planning iterations. To address these issues, we propose a new approach specifically tailored to the distinct features of the marine environment for navigation path planning of underwater vehicles, named bidirectional cached rapidly exploring random tree star (BCRRT*). By incorporating bidirectional path planning and caching algorithms on top of the RRT*, the search process can be expedited, and an efficient path connection can be achieved. When encountering new obstacles, ineffective portions of the cached path can be efficiently modified and severed, thus minimizing the computational workload while enhancing the algorithm’s adaptability. A certain number of simulation experiments were conducted, demonstrating that our proposed method outperformed cutting-edge techniques like the RRT* in several critical metrics such as the density of path nodes, planning time, and dynamic adaptability.

show abstract

Counter-Example Guided Imitation Learning of Feedback Controllers from Temporal Logic Specifications

Dang,

Donzé,

Haque

et al. 2023

2023 62nd IEEE Conference on Decision and Control (CDC)

View full text Add to dashboard Cite

Parallelized Control-Aware Motion Planning With Learned Controller Proxies

Cited by 4 publications

References 25 publications

Interleaving Graph Search and Trajectory Optimization for Aggressive Quadrotor Flight

Interleaving Graph Search and Trajectory Optimization for Aggressive Quadrotor Flight

Underwater Vehicle Path Planning Based on Bidirectional Path and Cached Random Tree Star Algorithm

Counter-Example Guided Imitation Learning of Feedback Controllers from Temporal Logic Specifications

Contact Info

Product

Resources

About