Long-Range Indoor Navigation With PRM-RL

Francis, Anthony G.; Faust, Aleksandra; Chiang, Hao-Tien Lewis; Hsu, Jasmine; Kew, J. Chase; Fišer, Marek; Lee, Tsang-Wei Edward

doi:10.1109/tro.2020.2975428

Cited by 116 publications

(72 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent research has offered several solutions for P2P obstacle-avoidance policies on a differential drive robot from raw sensory input, including learning from demonstration [20], curriculum learning [28], and reinforcement learning [25], [4]. Other research offers hierarchical solutions to navigation, where the RL agent executes a path identified by another planner, e.g., from a grid [5], PRMs [6], [8], or manually selected waypoints [11]. However, none of those methods are designed for kinodynamic robots, leading to failures at milestones due to dynamic constraints [8].…”

Section: Related Workmentioning

confidence: 99%

“…Other research offers hierarchical solutions to navigation, where the RL agent executes a path identified by another planner, e.g., from a grid [5], PRMs [6], [8], or manually selected waypoints [11]. However, none of those methods are designed for kinodynamic robots, leading to failures at milestones due to dynamic constraints [8].…”

Section: Related Workmentioning

confidence: 99%

“…The output of the training is a policy that is used as a local planner, an execution policy, and a data generation source for the obstacle-aware reachability estimator. Using one RL policy for both local planning and path execution is inspired by [8]. This allows the planner to account for potential noise during path execution.…”

Section: A Autorl Local Plannermentioning

confidence: 99%

“…As an example, we explain the training of the Asteroid robot here (details of the robot are in the Appendix). Details for the Differential Drive and Car robot can be found in [4] and [8]. The observation is a vector of 3N beams noisy lidar returns concatenated with the relative planar position of the goal, the robot velocity and orientation (3N beams + 5 dimensional vector).…”

Section: A Autorl Local Plannermentioning

confidence: 99%

“…We use pre-trained P2P policies for Fetch [4] and Car [8] robots. Their short description is available in the Appendix.…”

Section: B Autorl Policy Performancementioning

confidence: 99%

See 4 more Smart Citations

RL-RRT: Kinodynamic Motion Planning via Learning Reachability Estimators From RL Policies

Chiang

Hsu

Fišer

et al. 2019

IEEE Robot. Autom. Lett.

Self Cite

119

View full text Add to dashboard Cite

This paper addresses two challenges facing sampling-based kinodynamic motion planning: a way to identify good candidate states for local transitions and the subsequent computationally intractable steering between these candidate states. Through the combination of sampling-based planning, a Rapidly Exploring Randomized Tree (RRT) and an efficient kinodynamic motion planner through machine learning, we propose an efficient solution to long-range planning for kinodynamic motion planning. First, we use deep reinforcement learning to learn an obstacle-avoiding policy that maps a robot's sensor observations to actions, which is used as a local planner during planning and as a controller during execution. Second, we train a reachability estimator in a supervised manner, which predicts the RL policy's time to reach a state in the presence of obstacles. Lastly, we introduce RL-RRT that uses the RL policy as a local planner, and the reachability estimator as the distance function to bias tree-growth towards promising regions. We evaluate our method on three kinodynamic systems, including physical robot experiments. Results across all three robots tested indicate that RL-RRT outperforms state of the art kinodynamic planners in efficiency, and also provides a shorter path finish time than a steering function free method. The learned local planner policy and accompanying reachability estimator demonstrate transferability to the previously unseen experimental environments, making RL-RRT fast because the expensive computations are replaced with simple neural network inference. Video: https://youtu.be/dDMVMTOI8KY

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: A Autorl Local Plannermentioning

confidence: 99%

Section: A Autorl Local Plannermentioning

confidence: 99%

“…We use pre-trained P2P policies for Fetch [4] and Car [8] robots. Their short description is available in the Appendix.…”

Section: B Autorl Policy Performancementioning

confidence: 99%

See 3 more Smart Citations

RL-RRT: Kinodynamic Motion Planning via Learning Reachability Estimators From RL Policies

Chiang

Hsu

Fišer

et al. 2019

IEEE Robot. Autom. Lett.

Self Cite

119

View full text Add to dashboard Cite

show abstract

Classical versus reinforcement learning algorithms for unmanned aerial vehicle network communication and coverage path planning: A systematic literature review

Mannan

Obaidat

Mahmood

et al. 2022

Int J Communication

View full text Add to dashboard Cite

The unmanned aerial vehicle network communication includes all points of interest during the coverage path planning. Coverage path planning in such networks is crucial for many applications, such as surveying, monitoring, and disaster management. Since the coverage path planning belongs to NP-hard issues, researchers in this domain are constantly looking for optimal solutions for this task. The speed, direction, altitude, environmental variations, and obstacles make coverage path planning more difficult. Researchers have proposed numerous algorithms regarding coverage path planning. In this study, we examined and discussed existing state-of-the-art coverage path planning algorithms. We divided the existing techniques into two core categories: Classical and reinforcement learning. The classical algorithms are further divided into subcategories due to the availability of considerable variations in this category. For each algorithm in both types, we examined the issues of mobility, altitude, and characteristics of known and unknown environments. We also discuss the optimality of different algorithms. At the end of each section, we discuss the existing research gaps and provide future insights to overcome those gaps.

show abstract

Implementation of PID controller and enhanced red deer algorithm in optimal path planning of substation inspection robots

Tang,

Xue,

et al. 2024

Journal of Field Robotics

View full text Add to dashboard Cite

In contemporary power transmission systems, substation monitoring stands as a vital but challenging task. While robotics offers promise in this regard, its potential is still nascent, struggling to replicate human intelligence. This article's core aim was to optimize robot path planning (RPP). Employing the enhanced red deer algorithm (ERDA), we sought to bolster RPP for more efficient substation inspections. The key methods used seem to be modeling, experimentation, comparative analysis, and some elements of data benchmarking to systematically evaluate and validate their proposed technique and models both in simulation and the real world. Research aims to enhance substation inspection effectiveness and bolster the safety of power usage in society. Proposed hybrid approach, combining proportional–integral–derivative (PID) with ERDA (PID–ERDA), underpins an Intelligent Intelligent RPP framework tailored to substation inspections. Examining the PID–ERDA model's performance, it significantly improved path length by 18%–29% and reduced response times by 14%–26% compared with PID or ERDA alone. PID–ERDA consistently achieved optimal solutions in 40–60 trials out of 85, while PID and ERDA managed 20–40 trials with inconsistent optimization. Additionally, it reduced average response times to 17–20 s from 21 to 27 s observed when using PID and ERDA separately. PID–ERDA also demonstrated superior path accuracy, surpassing methods like improved adaptive control algorithm‐feedforward neural network, enhanced unified algorithm‐susceptible‐infected‐removed, and bounded behavior‐particle swarm optimization by 7%–13%. The study affirms that the PID–ERDA model significantly enhances path planning for substation inspections, representing a milestone in RPP for power station inspections within modern power transmission systems. The primary contribution of this research is the significant improvement it brings to RPP for power station inspections, especially in substation monitoring within modern power transmission systems.

show abstract

Long-Range Indoor Navigation With PRM-RL

Cited by 116 publications

References 69 publications

RL-RRT: Kinodynamic Motion Planning via Learning Reachability Estimators From RL Policies

RL-RRT: Kinodynamic Motion Planning via Learning Reachability Estimators From RL Policies

Classical versus reinforcement learning algorithms for unmanned aerial vehicle network communication and coverage path planning: A systematic literature review

Implementation of PID controller and enhanced red deer algorithm in optimal path planning of substation inspection robots

Contact Info

Product

Resources

About