Autonomous Algorithm for Training Autonomous Vehicles with Minimal Human Intervention

• URL: http://arxiv.org/abs/2405.13345v2
• Date: Thu, 16 Jan 2025 02:37:08 GMT
• Title: Autonomous Algorithm for Training Autonomous Vehicles with Minimal Human Intervention
• Authors: Sang-Hyun Lee, Daehyeok Kwon, Seung-Woo Seo,
• Abstract summary: reinforcement learning (RL) algorithms have demonstrated impressive results in simulated driving environments. RL algorithms can bypass the fidelity gap problem by directly training real-world autonomous vehicles. This paper introduces a novel algorithm that enables off-the-shelf RL algorithms to train autonomous vehicles with minimal human intervention.
• Score: 18.95571506577409
• License:
• Abstract: Recent reinforcement learning (RL) algorithms have demonstrated impressive results in simulated driving environments. However, autonomous vehicles trained in simulation often struggle to work well in the real world due to the fidelity gap between simulated and real-world environments. While directly training real-world autonomous vehicles with RL algorithms is a promising approach to bypass the fidelity gap problem, it presents several challenges. One critical yet often overlooked challenge is the need to reset a driving environment between every episode. This reset process demands significant human intervention, leading to poor training efficiency in the real world. In this paper, we introduce a novel autonomous algorithm that enables off-the-shelf RL algorithms to train autonomous vehicles with minimal human intervention. Our algorithm reduces unnecessary human intervention by aborting episodes to prevent unsafe states and identifying informative initial states for subsequent episodes. The key idea behind identifying informative initial states is to estimate the expected amount of information that can be obtained from under-explored but reachable states. Our algorithm also revisits rule-based autonomous driving algorithms and highlights their benefits in safely returning an autonomous vehicle to initial states. To evaluate how much human intervention is required during training, we implement challenging urban driving tasks that require an autonomous vehicle to reset to initial states on its own. The experimental results show that our autonomous algorithm is task-agnostic and achieves competitive driving performance with much less human intervention than baselines.

Related papers

• Mitigating Covariate Shift in Imitation Learning for Autonomous Vehicles Using Latent Space Generative World Models [60.87795376541144]
  A world model is a neural network capable of predicting an agent's next state given past states and actions. During end-to-end training, our policy learns how to recover from errors by aligning with states observed in human demonstrations. We present qualitative and quantitative results, demonstrating significant improvements upon prior state of the art in closed-loop testing.
  arXiv  Detail & Related papers  (2024-09-25T06:48:25Z)
• Work-in-Progress: Crash Course: Can (Under Attack) Autonomous Driving Beat Human Drivers? [60.51287814584477]
  This paper evaluates the inherent risks in autonomous driving by examining the current landscape of AVs. We develop specific claims highlighting the delicate balance between the advantages of AVs and potential security challenges in real-world scenarios.
  arXiv  Detail & Related papers  (2024-05-14T09:42:21Z)
• FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicing [71.76084256567599]
  We present a system that enables an autonomous small-scale RC car to drive aggressively from visual observations using reinforcement learning (RL) Our system, FastRLAP (faster lap), trains autonomously in the real world, without human interventions, and without requiring any simulation or expert demonstrations. The resulting policies exhibit emergent aggressive driving skills, such as timing braking and acceleration around turns and avoiding areas which impede the robot's motion, approaching the performance of a human driver using a similar first-person interface over the course of training.
  arXiv  Detail & Related papers  (2023-04-19T17:33:47Z)
• Comparative Study of Q-Learning and NeuroEvolution of Augmenting Topologies for Self Driving Agents [0.0]
  It is expected that autonomous driving can reduce the number of driving accidents around the world. We will focus reinforcement learning algorithms and NeuroEvolution of Augment Topologies (NEAT), a combination of evolutionary algorithms and artificial neural networks, to train a model agent to learn how to drive on a given path.
  arXiv  Detail & Related papers  (2022-09-19T13:34:18Z)
• Tackling Real-World Autonomous Driving using Deep Reinforcement Learning [63.3756530844707]
  In this work, we propose a model-free Deep Reinforcement Learning Planner training a neural network that predicts acceleration and steering angle. In order to deploy the system on board the real self-driving car, we also develop a module represented by a tiny neural network.
  arXiv  Detail & Related papers  (2022-07-05T16:33:20Z)
• Model-based Decision Making with Imagination for Autonomous Parking [50.41076449007115]
  The proposed algorithm consists of three parts: an imaginative model for anticipating results before parking, an improved rapid-exploring random tree (RRT) and a path smoothing module. Our algorithm is based on a real kinematic vehicle model; which makes it more suitable for algorithm application on real autonomous cars. In order to evaluate the algorithm's effectiveness, we have compared our algorithm with traditional RRT, within three different parking scenarios.
  arXiv  Detail & Related papers  (2021-08-25T18:24:34Z)
• Persistent Reinforcement Learning via Subgoal Curricula [114.83989499740193]
  Value-accelerated Persistent Reinforcement Learning (VaPRL) generates a curriculum of initial states. VaPRL reduces the interventions required by three orders of magnitude compared to episodic reinforcement learning.
  arXiv  Detail & Related papers  (2021-07-27T16:39:45Z)
• Vision-Based Autonomous Car Racing Using Deep Imitative Reinforcement Learning [13.699336307578488]
  Deep imitative reinforcement learning approach (DIRL) achieves agile autonomous racing using visual inputs. We validate our algorithm both in a high-fidelity driving simulation and on a real-world 1/20-scale RC-car with limited onboard computation.
  arXiv  Detail & Related papers  (2021-07-18T00:00:48Z)
• Deep Reinforcement Learning for Human-Like Driving Policies in Collision Avoidance Tasks of Self-Driving Cars [1.160208922584163]
  We introduce a model-free, deep reinforcement learning approach to generate automated human-like driving policies. We study a static obstacle avoidance task on a two-lane highway road in simulation. We demonstrate that our approach leads to human-like driving policies.
  arXiv  Detail & Related papers  (2020-06-07T18:20:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.