Autonomous driving faces challenges in navigating complex real-world traffic, requiring safe handling of both common and critical scenarios. Reinforcement learning (RL), a prominent method in end-to-end driving, enables agents to learn through trial and error in simulation. However, RL training often relies on rule-based traffic scenarios, limiting generalization. Additionally, current scenario generation methods focus heavily on critical scenarios, neglecting a balance with routine driving behaviors. Curriculum learning, which progressively trains agents on increasingly complex tasks, is a promising approach to improving the robustness and coverage of RL driving policies. However, existing research mainly emphasizes manually designed curricula, focusing on scenery and actor placement rather than traffic behavior dynamics. This work introduces a novel student-teacher framework for automatic curriculum learning. The teacher, a graph-based multi-agent RL component, adaptively generates traffic behaviors across diverse difficulty levels. An adaptive mechanism adjusts task difficulty based on student performance, ensuring exposure to behaviors ranging from common to critical. The student, though exchangeable, is realized as a deep RL agent with partial observability, reflecting real-world perception constraints. Results demonstrate the teacher’s ability to generate diverse traffic behaviors. The student, trained with automatic curricula, outperformed agents trained on rule-based traffic, achieving higher rewards and exhibiting balanced, assertive driving.

Accurate prediction of surrounding road users' trajectories is essential for safe and efficient autonomous driving. While deep learning models have improved performance, challenges remain in preventing off-road predictions and ensuring kinematic feasibility. Existing methods incorporate road-awareness modules and enforce kinematic constraints but lack plausibility guarantees and often introduce trade-offs in complexity and flexibility. This paper proposes a novel framework that formulates trajectory prediction as a constrained regression guided by permissible driving directions and their boundaries. Using the agent's current state and an HD map, our approach defines the valid boundaries and ensures on-road predictions by training the network to learn superimposed paths between left and right boundary polylines. To guarantee feasibility, the model predicts acceleration profiles that determine the vehicle's travel distance along these paths while adhering to kinematic constraints. We evaluate our approach on the Argoverse-2 dataset against the HPTR baseline. Our approach shows a slight decrease in benchmark metrics compared to HPTR but notably improves final displacement error and eliminates infeasible trajectories. Moreover, the proposed approach has a superior generalization to less prevalent maneuvers and unseen out-of-distribution scenarios, reducing the off-road rate under adversarial attacks from 66 % to just 1 %. These results highlight the effectiveness of our approach in generating feasible and robust predictions.

Reinforcement Learning (RL) is a promising approach for achieving autonomous driving due to robust decision-making capabilities. RL learns a driving policy through trial and error in traffic scenarios, guided by a reward function that combines the driving objectives. The design of such reward function has received insufficient attention, yielding ill-defined rewards with various pitfalls. Safety, in particular, has long been regarded only as a penalty for collisions. This leaves the risks associated with actions leading up to a collision unaddressed, limiting the applicability of RL in real-world scenarios. To address these shortcomings, our work focuses on enhancing the reward formulation by defining a set of driving objectives and structuring them hierarchically. Furthermore, we discuss the formulation of these objectives in a normalized manner to transparently determine their contribution to the overall reward. Additionally, we introduce a novel risk-aware objective for various driving interactions based on a two-dimensional ellipsoid function and an extension of Responsibility-Sensitive Safety (RSS) concepts. We evaluate the efficacy of our proposed reward in unsignalized intersection scenarios with varying traffic densities. The approach decreases collision rates by 21% on average compared to baseline rewards and consistently surpasses them in route progress and cumulative reward, demonstrating its capability to promote safer driving behaviors while maintaining high-performance levels.

This paper addresses the challenges of training end-to-end autonomous driving agents using Reinforcement Learning (RL). RL agents are typically trained in a fixed set of scenarios and nominal behavior of surrounding road users in simulations, limiting their generalization and real-life deployment. While Domain Randomization offers a potential solution by randomly sampling driving scenarios, it frequently results in inefficient training and sub-optimal policies due to the high variance among training scenarios. To address these limitations, we propose an automatic curriculum learning framework that dynamically generates driving scenarios with adaptive complexity based on the agent's evolving capabilities. Unlike manually designed curricula that introduce expert bias and lack scalability, our framework incorporates a “teacher” that automatically generates and mutates driving scenarios based on their learning potential-an agent-centric metric derived from the agent's current policy, eliminating the need for expert design. The framework enhances training efficiency by excluding scenarios the agent has mastered or finds too challenging. We evaluate our framework in a reinforcement learning setting where the agent learns a driving policy from camera images. Comparative results against baseline methods, including fixed scenario training and domain randomization, demonstrate that our approach leads to enhanced generalization, achieving higher success rates, +9 % in low traffic density, +21 % in high traffic density, and faster convergence with fewer training steps. Our findings highlight the potential of ACL in improving the robustness and efficiency of RL-based autonomous driving agents.

Trajectory prediction is crucial for autonomous driving, enabling vehicles to navigate safely by anticipating the movements of surrounding road users. However, current deep learning models often lack trustworthiness as their predictions can be physically infeasible and illogical to humans. To make predictions more trustworthy, recent research has incorporated prior knowledge, like the social force model for modeling interactions and kinematic models for physical realism. However, these approaches focus on priors that suit either vehicles or pedestrians and do not generalize to traffic with mixed agent classes. We propose incorporating interaction and kinematic priors of all agent classes-vehicles, pedestrians, and cyclists with class-specific interaction layers to capture agent behavioral differences. To improve the interpretability of the agent interactions, we introduce DG-SFM, a rule-based interaction importance score that guides the interaction layer. To ensure physically feasible predictions, we proposed suitable kinematic models for all agent classes with a novel pedestrian kinematic model. We benchmark our approach on the Argoverse 2 dataset, using the state-of-the-art transformer HPTR as our baseline. Experiments demonstrate that our method improves interaction interpretability, revealing a correlation between incorrect predictions and divergence from our interaction prior. Even though incorporating the kinematic models causes a slight decrease in accuracy, they eliminate infeasible trajectories found in the dataset and the baseline model. Thus, our approach fosters trust in trajectory prediction as its interaction reasoning is interpretable, and its predictions adhere to physics.

Reinforcement Learning is a highly active research field with promising advancements. In the field of autonomous driving, however, often very simple scenarios are being examined. Common approaches use non-interpretable control commands as the action space and unstructured reward designs, which are unsuitable for complex scenarios. In this work, we introduce Informed Reinforcement Learning, where a structured rulebook is integrated as a knowledge source. We learn trajectories and asses them with a situation-aware reward design, leading to a dynamic reward that allows the agent to learn situations that require controlled traffic rule exceptions. Our method is applicable to arbitrary RL models. We successfully demonstrate high completion rates of complex scenarios with recent model-based agents.

Reinforcement learning has emerged as an important approach for autonomous driving. A reward function is used in reinforcement learning to establish the learned skill objectives and guide the agent toward the optimal policy. Since autonomous driving is a complex domain with partly conflicting objectives with varying degrees of priority, developing a suitable reward function represents a fundamental challenge. This paper aims to highlight the gap in such function design by assessing different proposed formulations in the literature and dividing individual objectives into Safety, Comfort, Progress, and Traffic Rules compliance categories. Additionally, the limitations of the reviewed reward functions are discussed, such as objectives aggregation and indifference to driving context. Furthermore, the reward categories are frequently inadequately formulated and lack standardization. This paper concludes by proposing future research that potentially addresses the observed shortcomings in rewards, including a reward validation framework and structured rewards that are context-aware and able to resolve conflicts.

With consistently increasing amounts of transported goods, autonomous cargo transport has gained increasing interest as a potential solution. In addition to reliable autonomous driving functions, Autonomous cargo transport requires a wide range of additional software and hardware components to ensure a safe and efficient transport of cargo as well as a pleasant user experience for the customers. This work presents a general concept for an autonomous and flexible cargo transport system, targeting point-to-point transports in the range of the typical last mile. The proposed concept provides flexibility for demand-responsive passenger transport as a mixed cargo-passenger transport solution. Furthermore, the proposed concept is realized through designing a removable cargo hold with electronic locks, and software modules such as a Booking App, a Scanner App, and a central backend. The implementation was developed, deployed in an autonomous shuttle, and extensively tested in a peri-urban quarter of the Test Area Autonomous Driving Baden-Württemberg.

The accurate prediction of surrounding traffic actors’ movements is vital for the large-scale safe deployment of autonomous vehicles. Existing motion forecasting methods primarily aim to minimize prediction error by optimizing a loss function, which can sometimes lead to physically infeasible predictions or states that violate external constraints. This paper proposes a method that integrates explicit knowledge priors, allowing a network to forecast future trajectories that comply with both the vehicle’s kinematic constraints and the driving environment’s geometry. This is achieved by introducing a non-parametric pruning layer, and learnable attention layers to incorporate the defined knowledge priors. The proposed method aims to ensure reachability guarantees for traffic actors in both complex and dynamic situations. By conditioning the network to adhere to physical laws, we can achieve accurate and safe predictions, which are crucial for maintaining the safety and efficiency of autonomous vehicles in real-world settings.

Effective and flexible allocation of visual attention is key for pedestrians who have to navigate to a desired goal under different conditions of urgency and safety preferences. While automatic modelling of pedestrian attention holds great promise to improve simulations of pedestrian behavior, current saliency prediction approaches mostly focus on generic free-viewing scenarios and do not reflect the specific challenges present in pedestrian attention prediction. In this paper, we present Context-SalNET, a novel encoder-decoder architecture that explicitly addresses three key challenges of visual attention prediction in pedestrians: First, Context-SalNET explicitly models the context factors urgency and safety preference in the latent space of the encoder-decoder model. Second, we propose the exponentially weighted mean squared error loss (ew-MSE) that is able to better cope with the fact that only a small part of the ground truth saliency maps consist of non-zero entries. Third, we explicitly model epistemic uncertainty to account for the fact that training data for pedestrian attention prediction is limited. To evaluate Context-SalNET, we recorded the first dataset of pedestrian visual attention in VR that includes explicit variation of the context factors urgency and safety preference. Context-SalNET achieves clear improvements over state-of-the-art saliency prediction approaches as well as over ablations. Our novel dataset will be made fully available and can serve as a valuable resource for further research on pedestrian attention prediction.