Cola-HRL: Continuous-Lattice Hierarchical Reinforcement Learning for Autonomous Driving

Gao, Lingping; Gu, Ziqing; Qiu, Cong; Lei, Lanxin; Li, Shengbo Eben; Zheng, Sifa; Jing, Wei; Chen, Junbo

doi:10.1109/iros47612.2022.9982041

Cited by 9 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To improve model generalizability, Duan et al [138] split mobility responsibilities into three different models using a centralised policy network. Building on earlier research, Cola-HRL [139] combines a continuous-lattice state space representation, low-level controller, and high-level planner to provide higher making decisions efficiency across a range of scenarios as in comparison with state-of-the-art techniques.…”

Section: ) Hierarchical Rlmentioning

confidence: 99%

A Comprehensive Review on Deep Learning-Based Motion Planning and End-to-End Learning for Self-Driving Vehicle

Ganesan,

Kandhasamy,

Chokkalingam

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Self-Driving Vehicles (SDVs) are increasingly popular, with companies like Google, Uber, and Tesla investing significantly in self-driving technology. These vehicles could transform commuting, offering safer, and efficient transport. A key SDV aspect is motion planning, generating secure, and efficient routes. This ensures safe navigation and prevents collisions with obstacles, pedestrians, and other vehicles. Deep Learning (DL) could aid SDV motion planning. AI tools and algorithms, like Artificial Neural Networks (ANNs), Machine Learning (ML) and DL can learn from data to create effective driving strategies, enhancing SDV adaptability to changing conditions for improved safety and efficiency. This survey gives a DL-based motion planning overview for SDVs, covering behaviour planning, trajectory planning, and End to End Learning (E2EL). It assesses various DL-based behaviour and trajectory planning methods, comparing and summarizing them. It also reviews diverse E2EL techniques including Imitation Learning (IL) and Reinforcement Learning (RL) gaining traction lately. Additionally, this review emphasizes the significance of two crucial enablers: datasets and simulation deployment frameworks for SDVs. The survey compares strategies using multiple metrics and highlights DL-based SDV implementation challenges, including simulation and real-world use cases. This article also suggests future research directions to address E2EL and DL-based motion planning limitations. The presented article is an excellent reference for scholars, engineers, and decision-makers who have an interest in DL-based SDV motion planning.

show abstract

Section: ) Hierarchical Rlmentioning

confidence: 99%

A Comprehensive Review on Deep Learning-Based Motion Planning and End-to-End Learning for Self-Driving Vehicle

Ganesan,

Kandhasamy,

Chokkalingam

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The master policy network is trained to select the appropriate driving task, this policy greatly enhances the generalizability and effectiveness of the model. For the purpose of further improving decision quality in complex scenarios, Cola-HRL [112] is presented based on [110], this method consists of three main components: a high-level planner, a low-level controller, and a continuous-lattice representation of the state space. Both the planner and controller use the state space to generate high-quality decisions.…”

Section: ) Value-based Reinforcement Learningmentioning

confidence: 99%

Hierarchical Interpretable Imitation Learning for End-to-End Autonomous Driving

Teng

Chen

et al. 2023

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

Thanks to the augmented convenience, safety advantages, and potential commercial value, Intelligent vehicles (IVs) have attracted wide attention throughout the world. Although a few autonomous driving unicorns assert that IVs will be commercially deployable by 2025, their implementation is still restricted to small-scale validation due to various issues, among which precise computation of control commands or trajectories by planning methods remains a prerequisite for IVs. This paper aims to review state-of-the-art planning methods, including pipeline planning and end-to-end planning methods. In terms of pipeline methods, a survey of selecting algorithms is provided along with a discussion of the expansion and optimization mechanisms, whereas in end-to-end methods, the training approaches and verification scenarios of driving tasks are points of concern. Experimental platforms are reviewed to facilitate readers in selecting suitable training and validation methods. Finally, the current challenges and future directions are discussed. The sideby-side comparison presented in this survey not only helps to gain insights into the strengths and limitations of the reviewed methods but also assists with system-level design choices.

show abstract

“…Conventional rule-based approaches [3] have achieved some success in industry but require extensive human engineering to deal with diverse real-world scenarios. Recent advances in deep learning techniques have motivated researchers [4,5,6] to employ neural networks to model complex driving policies. Imitation learning (IL) from human drivers' demonstrations is a promising solution for learning these policies, as experienced drivers can handle even the most difficult situations, and their driving data can be easily collected at scale.…”

Section: Introductionmentioning

confidence: 99%

CCIL: Context-conditioned imitation learning for urban driving

Guo,

Jing,

Chen

et al. 2023

Robotics: Science and Systems XIX

View full text Add to dashboard Cite

Imitation learning holds great promise for addressing the complex task of autonomous urban driving, as experienced human drivers can navigate highly challenging scenarios with ease. While behavior cloning is a widely used imitation learning approach in autonomous driving due to its exemption from risky online interactions, it suffers from the covariate shift issue. To address this limitation, we propose a context-conditioned imitation learning approach that employs a policy to map the context state into the ego vehicle's future trajectory, rather than relying on the traditional formulation of both ego and context states to predict the ego action. Additionally, to reduce the implicit ego information in the coordinate system, we design an ego-perturbed goal-oriented coordinate system. The origin of this coordinate system is the ego vehicle's position plus a zero mean Gaussian perturbation, and the x-axis direction points towards its goal position. Our experiments on the real-world large-scale Lyft and nuPlan datasets show that our method significantly outperforms state-of-the-art approaches.

show abstract

Cola-HRL: Continuous-Lattice Hierarchical Reinforcement Learning for Autonomous Driving

Cited by 9 publications

References 32 publications

A Comprehensive Review on Deep Learning-Based Motion Planning and End-to-End Learning for Self-Driving Vehicle

A Comprehensive Review on Deep Learning-Based Motion Planning and End-to-End Learning for Self-Driving Vehicle

Hierarchical Interpretable Imitation Learning for End-to-End Autonomous Driving

CCIL: Context-conditioned imitation learning for urban driving

Contact Info

Product

Resources

About