Online, Model-Free Motion Planning in Dynamic Environments: An Intermittent, Finite Horizon Approach with Continuous-Time Q-Learning

Kontoudis, George P.; Xu, Zirui; Vamvoudakis, Kyriakos G.

doi:10.23919/acc45564.2020.9148047

Cited by 7 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although PRM-RL [88] and RL-RRT [89] both contain the high-level sampling-based planners with an RL-based local obstacle-avoiding policy, the latter RL agent can be deployed directly without the need of tuning reward and network structure. To achieve online and model-free kinodynamic planning, [90][91][92], were proposed. Benefiting from the vertex extension and metric role of the AC neural network, the framework can learn the optimal policy without model information to tackle every two-point boundary value problem from the RRTs.…”

Section: Motion Planning With Policy-based Rl Methodsmentioning

confidence: 99%

A survey of learning‐based robot motion planning

Wang

Zhang

et al. 2021

IET Cyber-Syst and Robotics

View full text Add to dashboard Cite

A fundamental task in robotics is to plan collision-free motions among a set of obstacles. Recently, learning-based motion-planning methods have shown significant advantages in solving different planning problems in high-dimensional spaces and complex environments. This article serves as a survey of various different learning-based methods that have been applied to robot motion-planning problems, including supervised, unsupervised learning, and reinforcement learning. These learning-based methods either rely on a human-crafted reward function for specific tasks or learn from successful planning experiences. The classical definition and learning-related definition of motion-planning problem are provided in this article. Different learning-based motion-planning algorithms are introduced, and the combination of classical motion-planning and learning techniques is discussed in detail.This is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.

show abstract

Section: Motion Planning With Policy-based Rl Methodsmentioning

confidence: 99%

A survey of learning‐based robot motion planning

Wang

Zhang

et al. 2021

IET Cyber-Syst and Robotics

View full text Add to dashboard Cite

show abstract

“…The authors of [24] developed a controller with intermittent communication for a multi-agent system, whose dwell-time conditions, needed for stability, as well as safety constraints were expressed by metric temporal logic specifications. Finally, event-triggering mechanisms were employed to the problem of autonomous path planning [25]. Compared to the aforementioned works, and to the best of our knowledge, this is the first time that an optimal, safe, and intermittent learning framework combined with formal methods is used in a continuous-time framework for tracking a family of trajectories.…”

Section: Related Workmentioning

confidence: 99%

“…We employ another approximating structure, called an actor, to approximate the intermittent controller (25). This is expressed, @t P pr j , r j`1 s, as u ‹ pŝ aug q " θ ‹ u T φ u pŝ aug q ` u pŝ aug q, @ŝ aug ,…”

Section: B Actor Approximatormentioning

confidence: 99%

Temporal-Logic-Based Intermittent, Optimal, and Safe Continuous-Time Learning for Trajectory Tracking

Kanellopoulos,

Fotiadis,

Sun

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper, we develop safe reinforcementlearning-based controllers for systems tasked with accomplishing complex missions that can be expressed as linear temporal logic specifications, similar to those required by search-andrescue missions. We decompose the original mission into a sequence of tracking sub-problems under safety constraints. We impose the safety conditions by utilizing barrier functions to map the constrained optimal tracking problem in the physical space to an unconstrained one in the transformed space. Furthermore, we develop policies that intermittently update the control signal to solve the tracking sub-problems with reduced burden in the communication and computation resources. Subsequently, an actor-critic algorithm is utilized to solve the underlying Hamilton-Jacobi-Bellman equations. Finally, we support our proposed framework with stability proofs and showcase its efficacy via simulation results.

show abstract