Utilizing Reinforcement Learning to Continuously Improve a Primitive-Based Motion Planner.

Goddard, Zachary; Wardlaw, Kenneth; Krishnan, Rohith; Tsiotras, Panagiotis; Smith, M. Hamblin; Sena, Mary Rose; Parish, Julie Marie-Jones; Mazumdar, Anirban

doi:10.2172/1836182

Cited by 3 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Under such a context, continuous feasibility and control liveliness are key concerns ensuring the accomplishment of higher level tasks, such as overtaking another slow vehicle, merging into a busy fast lane, or avoiding an obstacle at high speeds [117]. When selecting mode from a large library of complicated dynamic modes become computationally demanding, learning based approach such as reinforcement learning can be leveraged to efficiently learn the proper mode arbitration decision according to the environment [118], [119].…”

Section: Referencementioning

confidence: 99%

Formal Certification Methods for Automated Vehicle Safety Assessment

Zhao,

Yurtsever,

Paulson

et al. 2022

Preprint

View full text Add to dashboard Cite

Challenges related to automated driving are no longer focused on just the construction of such automated vehicles (AVs), but in assuring the safety of their operation. Recent advances in Level 3 and Level 4 autonomous driving have motivated more extensive study in safety guarantees of complicated AV maneuvers, which aligns with the goal of ISO 21448 (Safety of the Intended Functions, or SOTIF), i.e. minimizing unsafe scenarios both known and unknown, as well as Vision Zero -eliminating highway fatalities by 2050. A majority of approaches used in providing safety guarantees for AV motion control originate from formal methods, especially reachability analysis (RA), which relies on mathematical models for the dynamic evolution of the system to provide guarantees. However, to the best of the authors' knowledge, there have been no review papers dedicated to describing and interpreting state-of-the-art of formal methods in the context of AVs. In this work, we provide both an overview of the safety verification, validation and certification process, as well as review formal safety techniques that are best suited to AV applications. We also propose a unified scenario coverage framework that can provide either a formal or sample-based estimate of safety verification for full AVs. Finally, remaining challenges and future opportunities beyond the scope of current published research for assured AV safety are presented.

show abstract

Section: Referencementioning

confidence: 99%

Formal Certification Methods for Automated Vehicle Safety Assessment

Zhao,

Yurtsever,

Paulson

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The motion planning by MP approach has been extended by Frazzoli and his cofounders, as well as by several others, see, e.g., [5][6][7]12,[40][41][42]. However, some issues remain: first, the MP are specific to a certain system, e.g., a specific vehicle, since they typically depend on parameters.…”

Section: Shortcomingsmentioning

confidence: 99%

“…As an expansion of the library, Ref. [12] propose an exploration phase via reinforcement learning and, then, extracting and adding new trims and maneuvers to the initial library.…”

Section: Introductionmentioning

confidence: 99%

Learning Motion Primitives Automata for Autonomous Driving Applications

Pedrosa

Schneider

Flaßkamp

2022

MCA

View full text Add to dashboard Cite

Motion planning methods often rely on libraries of primitives. The selection of primitives is then crucial for assuring feasible solutions and good performance within the motion planner. In the literature, the library is usually designed by either learning from demonstration, relying entirely on data, or by model-based approaches, with the advantage of exploiting the dynamical system’s property, e.g., symmetries. In this work, we propose a method combining data with a dynamical model to optimally select primitives. The library is designed based on primitives with highest occurrences within the data set, while Lie group symmetries from a model are analysed in the available data to allow for structure-exploiting primitives. We illustrate our technique in an autonomous driving application. Primitives are identified based on data from human driving, with the freedom to build libraries of different sizes as a parameter of choice. We also compare the extracted library with a custom selection of primitives regarding the performance of obtained solutions for a street layout based on a real-world scenario.

show abstract

“…As a result, many past works have used Deep RL to solve a smaller part of the planning problem. For example, [26] used Deep RL to estimate reachability, [14] used RL for local planning, and [27][28][29] used RL to learn high-level actions (primitives).…”

Section: Introductionmentioning

confidence: 99%

Trajectory Planning with Deep Reinforcement Learning in High-Level Action Spaces

Williams¹,

Schlossman²,

Whitten³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

This paper presentsa technique for trajectory planning based on continuously parameterized high-level actions (motion primitives) of variable duration. This technique leverages deep reinforcement learning (Deep RL) to formulate a policy which is suitable for real-time implementation. There is no separation of motion primitive generation and trajectory planning: each individual short-horizon motion is formed during the Deep RL training to achieve the full-horizon objective. Effectiveness of the technique is demonstrated numerically on a well-studied trajectory generation problem and a planning problem on a known obstacle-rich map. This paper also develops a new loss function term for policy-gradient-based Deep RL, which is analogous to an anti-windup mechanism in feedback control. We demonstrate the inclusion of this new term in the underlying optimization increases the average policy return in our numerical example.

show abstract

Utilizing Reinforcement Learning to Continuously Improve a Primitive-Based Motion Planner.

Cited by 3 publications

References 0 publications

Formal Certification Methods for Automated Vehicle Safety Assessment

Formal Certification Methods for Automated Vehicle Safety Assessment

Learning Motion Primitives Automata for Autonomous Driving Applications

Trajectory Planning with Deep Reinforcement Learning in High-Level Action Spaces

Contact Info

Product

Resources

About