Reinforcement learning (RL) provides a compelling framework for enabling autonomous vehicles to continue to learn and improve diverse driving behaviors on their own. However, training real-world autonomous vehicles with current RL algorithms presents several challenges. One critical challenge, often overlooked in these algorithms, is the need to reset a driving environment between every episode. While resetting an environment after each episode is trivial in simulated settings, it demands significant human intervention in the real world. In this paper, we introduce a novel autonomous algorithm that allows off-the-shelf RL algorithms to train an autonomous vehicle with minimal human intervention. Our algorithm takes into account the learning progress of the autonomous vehicle to determine when to abort episodes before it enters unsafe states and where to reset it for subsequent episodes in order to gather informative transitions. The learning progress is estimated based on the novelty of both current and future states. We also take advantage of rule-based autonomous driving algorithms to safely reset an autonomous vehicle to an initial state. We evaluate our algorithm against baselines on diverse urban driving tasks. The experimental results show that our algorithm is task-agnostic and achieves better driving performance with fewer manual resets than baselines.

Autonomous vehicles have been actively investigated over the past few decades. Several recent works show the potential of autonomous vehicles in urban environments with impressive experimental results. However, these works note that autonomous vehicles are still occasionally inferior to expert drivers in complex scenarios. Furthermore, they do not focus on the possibilities of autonomous driving transportation services in other areas beyond urban environments. This paper presents the research results and lessons learned from autonomous driving transportation services in airfield, crowded indoor, and urban environments. We discuss how we address several unique challenges in these diverse environments. We also offer an overview of remaining challenges that have not received much attention but must be addressed. This paper aims to share our unique experience to support researchers who are interested in exploring autonomous driving transportation services in various real-world environments.

Hierarchical reinforcement learning (HRL) incorporates temporal abstraction into reinforcement learning (RL) by explicitly taking advantage of hierarchical structure. Modern HRL typically designs a hierarchical agent composed of a high-level policy and low-level policies. The high-level policy selects which low-level policy to activate at a lower frequency and the activated low-level policy selects an action at each time step. Recent HRL algorithms have achieved performance gains over standard RL algorithms in synthetic navigation tasks. However, we cannot apply these HRL algorithms to real-world navigation tasks. One of the main challenges is that real-world navigation tasks require an agent to perform safe and interactive behaviors in dynamic environments. In this paper, we propose imagination-augmented HRL (IAHRL) that efficiently integrates imagination into HRL to enable an agent to learn safe and interactive behaviors in real-world navigation tasks. Imagination is to predict the consequences of actions without interactions with actual environments. The key idea behind IAHRL is that the low-level policies imagine safe and structured behaviors, and then the high-level policy infers interactions with surrounding objects by interpreting the imagined behaviors. We also introduce a new attention mechanism that allows our high-level policy to be permutation-invariant to the order of surrounding objects and to prioritize our agent over them. To evaluate IAHRL, we introduce five complex urban driving tasks, which are among the most challenging real-world navigation tasks. The experimental results indicate that IAHRL enables an agent to perform safe and interactive behaviors, achieving higher success rates and lower average episode steps than baselines.

A significant bottleneck in applying current reinforcement learning algorithms to real-world scenarios is the need to reset the environment between every episode. This reset process demands substantial human intervention, making it difficult for the agent to learn continuously and autonomously. Several recent works have introduced autonomous reinforcement learning (ARL) algorithms that generate curricula for jointly training reset and forward policies. While their curricula can reduce the number of required manual resets by taking into account the agent's learning progress, they rely on task-specific knowledge, such as predefined initial states or reset reward functions. In this paper, we propose a novel ARL algorithm that can generate a curriculum adaptive to the agent's learning progress without task-specific knowledge. Our curriculum empowers the agent to autonomously reset to diverse and informative initial states. To achieve this, we introduce a success discriminator that estimates the success probability from each initial state when the agent follows the forward policy. The success discriminator is trained with relabeled transitions in a self-supervised manner. Our experimental results demonstrate that our ARL algorithm can generate an adaptive curriculum and enable the agent to efficiently bootstrap to solve sparse-reward maze navigation tasks, outperforming baselines with significantly fewer manual resets.

One of the unresolved challenges for autonomous vehicles is safe navigation among occluded pedestrians and vehicles. Previous approaches included generating phantom vehicles and assessing their risk, but they often made the ego vehicle overly conservative or could not conduct a real-time risk assessment in heavily occluded situations. We propose an efficient occlusion-aware risk assessment method using simplified reachability quantification that quantifies the reachability of phantom agents with a simple distribution model on phantom agents' state. Furthermore, we propose a driving strategy for safe and efficient navigation in occluded areas that sets the speed limit of an autonomous vehicle using the risk of phantom agents. Simulations were conducted to evaluate the performance of the proposed method in various occlusion scenarios involving other vehicles and obstacles. Compared with the baseline case of no occlusion-aware risk assessment, the proposed method increased the traversal time of an intersection by 1.48 times but decreased the average collision rate and discomfort score by up to 6.14 times and 5.03 times, respectively. The proposed method has shown the state-of-the-art level of time efficiency with constant time complexity and computational time less than 5 ms.