Ostap Okhrin

Fabian Hart, Ostap Okhrin, Martin Treiber

While deep reinforcement learning (RL) has been increasingly applied in designing car-following models in the last years, this study aims at investigating the feasibility of RL-based vehicle-following for complex vehicle dynamics and strong environmental disturbances. As a use case, we developed an inland waterways vessel-following model based on realistic vessel dynamics, which considers environmental influences, such as varying stream velocity and river profile. We extracted natural vessel behavior from anonymized AIS data to formulate a reward function that reflects a realistic driving style next to comfortable and safe navigation. Aiming at high generalization capabilities, we propose an RL training environment that uses stochastic processes to model leading trajectory and river dynamics. To validate the trained model, we defined different scenarios that have not been seen in training, including realistic vessel-following on the Middle Rhine. Our model demonstrated safe and comfortable driving in all scenarios, proving excellent generalization abilities. Furthermore, traffic oscillations could effectively be dampened by deploying the trained model on a sequence of following vessels.

Fabian Hart, Ostap Okhrin

In the field of autonomous robots, reinforcement learning (RL) is an increasingly used method to solve the task of dynamic obstacle avoidance for mobile robots, autonomous ships, and drones. A common practice to train those agents is to use a training environment with random initialization of agent and obstacles. Such approaches might suffer from a low coverage of high-risk scenarios in training, leading to impaired final performance of obstacle avoidance. This paper proposes a general training environment where we gain control over the difficulty of the obstacle avoidance task by using short training episodes and assessing the difficulty by two metrics: The number of obstacles and a collision risk metric. We found that shifting the training towards a greater task difficulty can massively increase the final performance. A baseline agent, using a traditional training environment based on random initialization of agent and obstacles and longer training episodes, leads to a significantly weaker performance. To prove the generalizability of the proposed approach, we designed two realistic use cases: A mobile robot and a maritime ship under the threat of approaching obstacles. In both applications, the previous results can be confirmed, which emphasizes the general usability of the proposed approach, detached from a specific application context and independent of the agent's dynamics. We further added Gaussian noise to the sensor signals, resulting in only a marginal degradation of performance and thus indicating solid robustness of the trained agent.

Martin Waltz, Ostap Okhrin

This paper proposes a spatial-temporal recurrent neural network architecture for deep $Q$-networks that can be used to steer an autonomous ship. The network design makes it possible to handle an arbitrary number of surrounding target ships while offering robustness to partial observability. Furthermore, a state-of-the-art collision risk metric is proposed to enable an easier assessment of different situations by the agent. The COLREG rules of maritime traffic are explicitly considered in the design of the reward function. The final policy is validated on a custom set of newly created single-ship encounters called `Around the Clock' problems and the commonly used Imazu (1987) problems, which include 18 multi-ship scenarios. Performance comparisons with artificial potential field and velocity obstacle methods demonstrate the potential of the proposed approach for maritime path planning. Furthermore, the new architecture exhibits robustness when it is deployed in multi-agent scenarios and it is compatible with other deep reinforcement learning algorithms, including actor-critic frameworks.

Niklas Paulig, Ostap Okhrin

This paper develops a Deep Reinforcement Learning (DRL)-agent for navigation and control of autonomous surface vessels (ASV) on inland waterways. Spatial restrictions due to waterway geometry and the resulting challenges, such as high flow velocities or shallow banks, require controlled and precise movement of the ASV. A state-of-the-art bootstrapped Q-learning algorithm in combination with a versatile training environment generator leads to a robust and accurate rudder controller. To validate our results, we compare the path-following capabilities of the proposed approach to a vessel-specific PID controller on real-world river data from the lower- and middle Rhine, indicating that the DRL algorithm could effectively prove generalizability even in never-seen scenarios while simultaneously attaining high navigational accuracy.

Dianzhao Li, Ostap Okhrin

Deep Reinforcement Learning (DRL) has shown remarkable success in solving complex tasks across various research fields. However, transferring DRL agents to the real world is still challenging due to the significant discrepancies between simulation and reality. To address this issue, we propose a robust DRL framework that leverages platform-dependent perception modules to extract task-relevant information and train a lane-following and overtaking agent in simulation. This framework facilitates the seamless transfer of the DRL agent to new simulated environments and the real world with minimal effort. We evaluate the performance of the agent in various driving scenarios in both simulation and the real world, and compare it to human players and the PID baseline in simulation. Our proposed framework significantly reduces the gaps between different platforms and the Sim2Real gap, enabling the trained agent to achieve similar performance in both simulation and the real world, driving the vehicle effectively.

Fabian Hart, Martin Waltz, Ostap Okhrin

Dynamic obstacle avoidance (DOA) is a fundamental challenge for any autonomous vehicle, independent of whether it operates in sea, air, or land. This paper proposes a two-step architecture for handling DOA tasks by combining supervised and reinforcement learning (RL). In the first step, we introduce a data-driven approach to estimate the collision risk (CR) of an obstacle using a recurrent neural network, which is trained in a supervised fashion and offers robustness to non-linear obstacle movements. In the second step, we include these CR estimates into the observation space of an RL agent to increase its situational awareness. We illustrate the power of our two-step approach by training different RL agents in a challenging environment that requires to navigate amid multiple obstacles. The non-linear movements of obstacles are exemplarily modeled based on stochastic processes and periodic patterns, although our architecture is suitable for any obstacle dynamics. The experiments reveal that integrating our CR metrics into the observation space doubles the performance in terms of reward, which is equivalent to halving the number of collisions in the considered environment. We also perform a generalization experiment to validate the proposal in an RL environment based on maritime traffic and real-world vessel trajectory data. Furthermore, we show that the architecture's performance improvement is independent of the applied RL algorithm.

Martin Waltz, Niklas Paulig, Ostap Okhrin

This paper proposes a realistic modularized framework for controlling autonomous surface vehicles (ASVs) on inland waterways (IWs) based on deep reinforcement learning (DRL). The framework improves operational safety and comprises two levels: a high-level local path planning (LPP) unit and a low-level path following (PF) unit, each consisting of a DRL agent. The LPP agent is responsible for planning a path under consideration of dynamic vessels, closing a gap in the current research landscape. In addition, the LPP agent adequately considers traffic rules and the geometry of the waterway. We thereby introduce a novel application of a spatial-temporal recurrent neural network architecture to continuous action spaces. The LPP agent outperforms a state-of-the-art artificial potential field (APF) method by increasing the minimum distance to other vessels by 65% on average. The PF agent performs low-level actuator control while accounting for shallow water influences and the environmental forces winds, waves, and currents. Compared with a proportional-integral-derivative (PID) controller, the PF agent yields only 61% of the mean cross-track error (MCTE) while significantly reducing control effort (CE) in terms of the required absolute rudder angle. Lastly, both agents are jointly validated in simulation, employing the lower Elbe in northern Germany as an example case and using real automatic identification system (AIS) trajectories to model the behavior of other ships.

Guangli Chen, Dianzhao Li, Wenjian Zhong et al.

Robust urban autonomous driving requires reliable 3D scene understanding and stable decision-making under dense interactions. However, existing end-to-end models lack interpretability, while modular pipelines suffer from error propagation across brittle interfaces. This paper proposes MTA-RL, the first framework that bridges perception and control through Multi-modal Transformer-based 3D Affordances and Reinforcement Learning (RL). Unlike previous fusion models that directly regress actions, RGB images and LiDAR point clouds are fused using a transformer architecture to predict explicit, geometry-aware affordance representations. These structured representations serve as a compact observation space, enabling the RL policy to operate purely on predicted driving semantics, which significantly improves sample efficiency and stability. Extensive evaluations in CARLA Town01-03 across varying densities (20-60 background vehicles) show that MTA-RL consistently outperforms state-of-the-art baselines. Trained solely on Town03, our method demonstrates superior zero-shot generalization in unseen towns, achieving up to a 9.0% increase in Route Completion, an 11.0% increase in Total Distance, and an 83.7% improvement in Distance Per Violation. Furthermore, ablation studies confirm that our multi-modal fusion and reward shaping are critical, significantly outperforming image-only and unshaped variants, demonstrating the effectiveness of MTA-RL for robust urban autonomous driving.

Dianzhao Li, Paul Auerbach, Ostap Okhrin

While engaging with the unfolding revolution in autonomous driving, a challenge presents itself, how can we effectively raise awareness within society about this transformative trend? While full-scale autonomous driving vehicles often come with a hefty price tag, the emergence of small-scale car platforms offers a compelling alternative. These platforms not only serve as valuable educational tools for the broader public and young generations but also function as robust research platforms, contributing significantly to the ongoing advancements in autonomous driving technology. This survey outlines various small-scale car platforms, categorizing them and detailing the research advancements accomplished through their usage. The conclusion provides proposals for promising future directions in the field.

Martin Waltz, Ostap Okhrin, Michael Schultz

Urban air mobility is an innovative mode of transportation in which electric vertical takeoff and landing (eVTOL) vehicles operate between nodes called vertiports. We outline a self-organized vertiport arrival system based on deep reinforcement learning. The airspace around the vertiport is assumed to be circular, and the vehicles can freely operate inside. Each aircraft is considered an individual agent and follows a shared policy, resulting in decentralized actions that are based on local information. We investigate the development of the reinforcement learning policy during training and illustrate how the algorithm moves from suboptimal local holding patterns to a safe and efficient final policy. The latter is validated in simulation-based scenarios, including robustness analyses against sensor noise and a changing distribution of inbound traffic. Lastly, we deploy the final policy on small-scale unmanned aerial vehicles to showcase its real-world usability.

Dianzhao Li, Ostap Okhrin

Autonomous vehicles hold great promise for reducing traffic fatalities and improving transportation efficiency, yet their widespread adoption hinges on embedding credible and transparent ethical reasoning into routine and emergency maneuvers, particularly to protect vulnerable road users (VRUs) such as pedestrians and cyclists. Here, we present a hierarchical Safe Reinforcement Learning (Safe RL) framework that augments standard driving objectives with ethics-aware cost signals. At the decision level, a Safe RL agent is trained using a composite ethical risk cost, combining collision probability and harm severity, to generate high-level motion targets. A dynamic, risk-sensitive Prioritized Experience Replay mechanism amplifies learning from rare but critical, high-risk events. At the execution level, polynomial path planning coupled with Proportional-Integral-Derivative (PID) and Stanley controllers translates these targets into smooth, feasible trajectories, ensuring both accuracy and comfort. We train and validate our approach on closed-loop simulation environments derived from large-scale, real-world traffic datasets encompassing diverse vehicles, cyclists, and pedestrians, and demonstrate that it outperforms baseline methods in reducing risk to others while maintaining ego performance and comfort. This work provides a reproducible benchmark for Safe RL with explicitly ethics-aware objectives in human-mixed traffic scenarios. Our results highlight the potential of combining formal control theory and data-driven learning to advance ethically accountable autonomy that explicitly protects those most at risk in urban traffic environments. Across two interactive benchmarks and five random seeds, our policy decreases conflict frequency by 25-45% compared to matched task successes while maintaining comfort metrics within 5%.

Dianzhao Li, Ostap Okhrin

To achieve fully autonomous driving, vehicles must be capable of continuously performing various driving tasks, including lane keeping and car following, both of which are fundamental and well-studied driving ones. However, previous studies have mainly focused on individual tasks, and car following tasks have typically relied on complete leader-follower information to attain optimal performance. To address this limitation, we propose a vision-based deep reinforcement learning (DRL) agent that can simultaneously perform lane keeping and car following maneuvers. To evaluate the performance of our DRL agent, we compare it with a baseline controller and use various performance metrics for quantitative analysis. Furthermore, we conduct a real-world evaluation to demonstrate the Sim2Real transfer capability of the trained DRL agent. To the best of our knowledge, our vision-based car following and lane keeping agent with Sim2Real transfer capability is the first of its kind.

Martin Waltz, Ostap Okhrin

Value-based reinforcement-learning algorithms have shown strong results in games, robotics, and other real-world applications. Overestimation bias is a known threat to those algorithms and can sometimes lead to dramatic performance decreases or even complete algorithmic failure. We frame the bias problem statistically and consider it an instance of estimating the maximum expected value (MEV) of a set of random variables. We propose the $T$-Estimator (TE) based on two-sample testing for the mean, that flexibly interpolates between over- and underestimation by adjusting the significance level of the underlying hypothesis tests. We also introduce a generalization, termed $K$-Estimator (KE), that obeys the same bias and variance bounds as the TE and relies on a nearly arbitrary kernel function. We introduce modifications of $Q$-Learning and the Bootstrapped Deep $Q$-Network (BDQN) using the TE and the KE, and prove convergence in the tabular setting. Furthermore, we propose an adaptive variant of the TE-based BDQN that dynamically adjusts the significance level to minimize the absolute estimation bias. All proposed estimators and algorithms are thoroughly tested and validated on diverse tasks and environments, illustrating the bias control and performance potential of the TE and KE.

Dianzhao Li, Ostap Okhrin

In the autonomous driving field, fusion of human knowledge into Deep Reinforcement Learning (DRL) is often based on the human demonstration recorded in a simulated environment. This limits the generalization and the feasibility of application in real-world traffic. We propose a two-stage DRL method to train a car-following agent, that modifies the policy by leveraging the real-world human driving experience and achieves performance superior to the pure DRL agent. Training a DRL agent is done within CARLA framework with Robot Operating System (ROS). For evaluation, we designed different driving scenarios to compare the proposed two-stage DRL car-following agent with other agents. After extracting the "good" behavior from the human driver, the agent becomes more efficient and reasonable, which makes this autonomous agent more suitable for Human-Robot Interaction (HRI) traffic.

Fabian Hart, Martin Waltz, Ostap Okhrin

We introduce a novel approach to dynamic obstacle avoidance based on Deep Reinforcement Learning by defining a traffic type independent environment with variable complexity. Filling a gap in the current literature, we thoroughly investigate the effect of missing velocity information on an agent's performance in obstacle avoidance tasks. This is a crucial issue in practice since several sensors yield only positional information of objects or vehicles. We evaluate frequently-applied approaches in scenarios of partial observability, namely the incorporation of recurrency in the deep neural networks and simple frame-stacking. For our analysis, we rely on state-of-the-art model-free deep RL algorithms. The lack of velocity information is found to significantly impact the performance of an agent. Both approaches - recurrency and frame-stacking - cannot consistently replace missing velocity information in the observation space. However, in simplified scenarios, they can significantly boost performance and stabilize the overall training procedure.

Fabian Hart, Ostap Okhrin, Martin Treiber

We propose and validate a novel car following model based on deep reinforcement learning. Our model is trained to maximize externally given reward functions for the free and car-following regimes rather than reproducing existing follower trajectories. The parameters of these reward functions such as desired speed, time gap, or accelerations resemble that of traditional models such as the Intelligent Driver Model (IDM) and allow for explicitly implementing different driving styles. Moreover, they partially lift the black-box nature of conventional neural network models. The model is trained on leading speed profiles governed by a truncated Ornstein-Uhlenbeck process reflecting a realistic leader's kinematics. This allows for arbitrary driving situations and an infinite supply of training data. For various parameterizations of the reward functions, and for a wide variety of artificial and real leader data, the model turned out to be unconditionally string stable, comfortable, and crash-free. String stability has been tested with a platoon of five followers following an artificial and a real leading trajectory. A cross-comparison with the IDM calibrated to the goodness-of-fit of the relative gaps showed a higher reward compared to the traditional model and a better goodness-of-fit.