Many settings of interest involving humans and machines -- from virtual personal assistants to autonomous vehicles -- can naturally be modelled as principals (humans) delegating to agents (machines), which then interact with each other on their principals' behalf. We refer to these multi-principal, multi-agent scenarios as delegation games. In such games, there are two important failure modes: problems of control (where an agent fails to act in line their principal's preferences) and problems of cooperation (where the agents fail to work well together). In this paper we formalise and analyse these problems, further breaking them down into issues of alignment (do the players have similar preferences?) and capabilities (how competent are the players at satisfying those preferences?). We show -- theoretically and empirically -- how these measures determine the principals' welfare, how they can be estimated using limited observations, and thus how they might be used to help us design more aligned and cooperative AI systems.
High-definition (HD) Map systems will play a pivotal role in advancing autonomous driving to a higher level, thanks to the significant improvement over traditional two-dimensional (2D) maps. Creating an HD Map requires a huge amount of on-road and off-road data. Typically, these raw datasets are collected and uploaded to cloud-based HD map service providers through vehicular networks. Nevertheless, there are challenges in transmitting the raw data over vehicular wireless channels due to the dynamic topology. As the number of vehicles increases, there is a detrimental impact on service quality, which acts as a barrier to a real-time HD Map system for collaborative driving in Autonomous Vehicles (AV). In this paper, to overcome network congestion, a Q-learning coverage-time-awareness algorithm is presented to optimize the quality of service for vehicular networks and HD map updates. The algorithm is evaluated in an environment that imitates a dynamic scenario where vehicles enter and leave. Results showed an improvement in latency for HD map data of $75\%$, $73\%$, and $10\%$ compared with IEEE802.11p without Quality of Service (QoS), IEEE802.11 with QoS, and IEEE802.11p with new access category (AC) for HD map, respectively.
The increasing interest in Autonomous Vehicles (AV) is notable due to business, safety, and performance reasons. While there is salient success in recent AV architectures, hinging on the advancements in AI models, there is a growing number of fatal incidents that impedes full AVs from going mainstream. This calls for the need to revisit the fundamentals of building safety-critical AV architectures. However, this direction should not deter leveraging the power of AI. To this end, we propose Savvy, a new trustworthy intelligent AV architecture that achieves the best of both worlds. Savvy makes a clear separation between the control plane and the data plane to guarantee the safety-first principles. The former assume control to ensure safety using design-time defined rules, while launching the latter for optimizing decisions as much as possible within safety time-bounds. This is achieved through guided Time-aware predictive quality degradation (TPQD): using dynamic ML models that can be tuned to provide either richer or faster outputs based on the available safety time bounds. For instance, Savvy allows to safely identify an elephant as an obstacle (a mere object) the earliest possible, rather than optimally recognizing it as an elephant when it is too late. This position paper presents the Savvy's motivations and concept, whereas empirical evaluation is a work in progress.
Technological advancements focus on developing comfortable and acceptable driving characteristics in autonomous vehicles. Present driving functions predominantly possess predefined parameters, and there is no universally accepted driving style for autonomous vehicles. While driving may be technically safe and the likelihood of road accidents is reduced, passengers may still feel insecure due to a mismatch in driving styles between the human and the autonomous system. Incorporating driving style preferences into automated vehicles enhances acceptance, reduces uncertainty, and poses the opportunity to expedite their adoption. Despite the increased research focus on driving styles, there remains a need for comprehensive studies investigating how variations in the driving context impact the assessment of automated driving functions. Therefore, this work evaluates lateral driving style preferences for autonomous vehicles on rural roads, considering different weather and traffic situations. A controlled study was conducted with a variety of German participants utilizing a high-fidelity driving simulator. The subjects experienced four different driving styles, including mimicking of their own driving behavior under two weather conditions. A notable preference for a more passive driving style became evident based on statistical analyses of participants' responses during and after the drives. This study could not confirm the hypothesis that subjects prefer to be driven by mimicking their own driving behavior. Furthermore, the study illustrated that weather conditions and oncoming traffic substantially influence the perceived comfort during autonomous rides. The gathered dataset is openly accessible at https://www.kaggle.com/datasets/jhaselberger/idcld-subject-study-on-driving-style-preferences.
The metaverse is a virtual space that combines physical and digital elements, creating immersive and connected digital worlds. For autonomous mobility, it enables new possibilities with edge computing and digital twins (DTs) that offer virtual prototyping, prediction, and more. DTs can be created with 3D scene reconstruction methods that capture the real world's geometry, appearance, and dynamics. However, sending data for real-time DT updates in the metaverse, such as camera images and videos from connected autonomous vehicles (CAVs) to edge servers, can increase network congestion, costs, and latency, affecting metaverse services. Herein, a new method is proposed based on distributed radiance fields (RFs), multi-access edge computing (MEC) network for video compression and metaverse DT updates. RF-based encoder and decoder are used to create and restore representations of camera images. The method is evaluated on a dataset of camera images from the CARLA simulator. Data savings of up to 80% were achieved for H.264 I-frame - P-frame pairs by using RFs instead of I-frames, while maintaining high peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) qualitative metrics for the reconstructed images. Possible uses and challenges for the metaverse and autonomous mobility are also discussed.
As intelligent robots like autonomous vehicles become increasingly deployed in the presence of people, the extent to which these systems should leverage model-based game-theoretic planners versus data-driven policies for safe, interaction-aware motion planning remains an open question. Existing dynamic game formulations assume all agents are task-driven and behave optimally. However, in reality, humans tend to deviate from the decisions prescribed by these models, and their behavior is better approximated under a noisy-rational paradigm. In this work, we investigate a principled methodology to blend a data-driven reference policy with an optimization-based game-theoretic policy. We formulate KLGame, an algorithm for solving non-cooperative dynamic game with Kullback-Leibler (KL) regularization with respect to a general, stochastic, and possibly multi-modal reference policy. Our method incorporates, for each decision maker, a tunable parameter that permits modulation between task-driven and data-driven behaviors. We propose an efficient algorithm for computing multi-modal approximate feedback Nash equilibrium strategies of KLGame in real time. Through a series of simulated and real-world autonomous driving scenarios, we demonstrate that KLGame policies can more effectively incorporate guidance from the reference policy and account for noisily-rational human behaviors versus non-regularized baselines. Website with additional information, videos, and code: https://kl-games.github.io/.
Autonomous vehicles trained through Multi-Agent Reinforcement Learning (MARL) have shown impressive results in many driving scenarios. However, the performance of these trained policies can be impacted when faced with diverse driving styles and personalities, particularly in highly interactive situations. This is because conventional MARL algorithms usually operate under the assumption of fully cooperative behavior among all agents and focus on maximizing team rewards during training. To address this issue, we introduce the Personality Modeling Network (PeMN), which includes a cooperation value function and personality parameters to model the varied interactions in high-interactive scenarios. The PeMN also enables the training of a background traffic flow with diverse behaviors, thereby improving the performance and generalization of the ego vehicle. Our extensive experimental studies, which incorporate different personality parameters in high-interactive driving scenarios, demonstrate that the personality parameters effectively model diverse driving styles and that policies trained with PeMN demonstrate better generalization compared to traditional MARL methods.
Large Language Models (LLMs) have garnered significant attention for their ability to understand text and images, generate human-like text, and perform complex reasoning tasks. However, their ability to generalize this advanced reasoning with a combination of natural language text for decision-making in dynamic situations requires further exploration. In this study, we investigate how well LLMs can adapt and apply a combination of arithmetic and common-sense reasoning, particularly in autonomous driving scenarios. We hypothesize that LLMs hybrid reasoning abilities can improve autonomous driving by enabling them to analyze detected object and sensor data, understand driving regulations and physical laws, and offer additional context. This addresses complex scenarios, like decisions in low visibility (due to weather conditions), where traditional methods might fall short. We evaluated Large Language Models (LLMs) based on accuracy by comparing their answers with human-generated ground truth inside CARLA. The results showed that when a combination of images (detected objects) and sensor data is fed into the LLM, it can offer precise information for brake and throttle control in autonomous vehicles across various weather conditions. This formulation and answers can assist in decision-making for auto-pilot systems.
The problem of 3D high-resolution imaging in automotive multiple-input multiple-output (MIMO) side-looking radar using a 1D array is considered. The concept of motion-enhanced snapshots is introduced for generating larger apertures in the azimuth dimension. For the first time, 3D imaging capabilities can be achieved with high angular resolution using a 1D MIMO antenna array, which can alleviate the requirement for large radar systems in autonomous vehicles. The robustness to variations in the vehicle's movement trajectory is also considered and addressed with relevant compensations in the steering vector. The available degrees of freedom as well as the Signal to Noise Ratio (SNR) are shown to increase with the proposed method compared to conventional imaging approaches. The performance of the algorithm has been studied in simulations, and validated with experimental data collected in a realistic driving scenario.
Advancements in technology are steering attention toward creating comfortable and acceptable driving characteristics in autonomous vehicles. Ensuring a safe and comfortable ride experience is vital for the widespread adoption of autonomous vehicles, as mismatches in driving styles between humans and autonomous systems can impact passenger confidence. Current driving functions have fixed parameters, and there is no universally agreed-upon driving style for autonomous vehicles. Integrating driving style preferences into automated vehicles may enhance acceptance and reduce uncertainty, expediting their adoption. A controlled vehicle study (N = 62) was conducted with a variety of German participants to identify the individual lateral driving behavior of human drivers, specifically emphasizing rural roads. We introduce novel indicators for assessing stationary and transient curve negotiation, directly applicable in developing personalized lateral driving functions. To assess the predictability of these indicators using self-reports, we introduce the MDSI-DE, the German version of the Multidimensional Driving Style Inventory. The correlation analysis between MDSI factor scores and proposed indicators showed modest but significant associations, primarily with acceleration and jerk statistics while the in-depth lateral driving behavior turned out to be highly driver-heterogeneous. The dataset including the anonymized socio-demographics and questionnaire responses, the raw vehicle measurements including labels, and the derived driving behavior indicators are publicly available at https://www.kaggle.com/datasets/jhaselberger/spodb-subject-study-of-lateral-vehicle-guidance.
Previous studies in predicting crash risks primarily associated the number or likelihood of crashes on a road segment with traffic parameters or geometric characteristics, usually neglecting the impact of vehicles' continuous movement and interactions with nearby vehicles. Recent technology advances, such as Connected and Automated Vehicles (CAVs) and Unmanned Aerial Vehicles (UAVs) are able to collect high-resolution trajectory data, which enables trajectory-based risk analysis. This study investigates a new vehicle group (VG) based risk analysis method and explores risk evolution mechanisms considering VG features. An impact-based vehicle grouping method is proposed to cluster vehicles into VGs by evaluating their responses to the erratic behaviors of nearby vehicles. The risk of a VG is aggregated based on the risk between each vehicle pair in the VG, measured by inverse Time-to-Collision (iTTC). A Logistic Regression and a Graph Neural Network (GNN) are then employed to predict VG risks using aggregated and disaggregated VG information. Both methods achieve excellent performance with AUC values exceeding 0.93. For the GNN model, GNNExplainer with feature perturbation is applied to identify critical individual vehicle features and their directional impact on VG risks. Overall, this research contributes a new perspective for identifying, predicting, and interpreting traffic risks.
Accurate pedestrian intention prediction (PIP) by Autonomous Vehicles (AVs) is one of the current research challenges in this field. In this article, we introduce PIP-Net, a novel framework designed to predict pedestrian crossing intentions by AVs in real-world urban scenarios. We offer two variants of PIP-Net designed for different camera mounts and setups. Leveraging both kinematic data and spatial features from the driving scene, the proposed model employs a recurrent and temporal attention-based solution, outperforming state-of-the-art performance. To enhance the visual representation of road users and their proximity to the ego vehicle, we introduce a categorical depth feature map, combined with a local motion flow feature, providing rich insights into the scene dynamics. Additionally, we explore the impact of expanding the camera's field of view, from one to three cameras surrounding the ego vehicle, leading to enhancement in the model's contextual perception. Depending on the traffic scenario and road environment, the model excels in predicting pedestrian crossing intentions up to 4 seconds in advance which is a breakthrough in current research studies in pedestrian intention prediction. Finally, for the first time, we present the Urban-PIP dataset, a customised pedestrian intention prediction dataset, with multi-camera annotations in real-world automated driving scenarios.
Guaranteeing the safe operations of autonomous vehicles (AVs) is crucial for their widespread adoption and public acceptance. It is thus of a great significance to not only assess the AV against the standard safety tests, but also discover potential corner cases of the AV under test that could lead to unsafe behaviour or scenario. In this paper, we propose a novel framework to systematically explore corner cases that can result in safety concerns in a highway traffic scenario. The framework is based on an adaptive stress testing (AST) approach, an emerging validation method that leverages a Markov decision process to formulate the scenarios and deep reinforcement learning (DRL) to discover the desirable patterns representing corner cases. To this end, we develop a new reward function for DRL to guide the AST in identifying crash scenarios based on the collision probability estimate between the AV under test (i.e., the ego vehicle) and the trajectory of other vehicles on the highway. The proposed framework is further integrated with a new driving model enabling us to create more realistic traffic scenarios capturing both the longitudinal and lateral movements of vehicles on the highway. In our experiment, we calibrate our model using real-world crash statistics involving automated vehicles in California, and then we analyze the characteristics of the AV and the framework. Quantitative and qualitative analyses of our experimental results demonstrate that our framework outperforms other existing AST schemes. The study can help discover crash scenarios of AV that are unknown or absent in human driving, thereby enhancing the safety and trustworthiness of AV technology.
Autonomous vehicles are suited for continuous area patrolling problems. Finding an optimal patrolling strategy can be challenging due to unknown environmental factors, such as wind or landscape; or autonomous vehicles' constraints, such as limited battery life or hardware failures. Importantly, patrolling large areas often requires multiple agents to collectively coordinate their actions. However, an optimal coordination strategy is often non-trivial to be manually defined due to the complex nature of patrolling environments. In this paper, we consider a patrolling problem with environmental factors, agent limitations, and three typical cooperation problems -- collision avoidance, congestion avoidance, and patrolling target negotiation. We propose a multi-agent reinforcement learning solution based on a reinforced inter-agent learning (RIAL) method. With this approach, agents are trained to develop their own communication protocol to cooperate during patrolling where faults can and do occur. The solution is validated through simulation experiments and is compared with several state-of-the-art patrolling solutions from different perspectives, including the overall patrol performance, the collision avoidance performance, the efficiency of battery recharging strategies, and the overall fault tolerance.
Large-scale 3D scene reconstruction and novel view synthesis are vital for autonomous vehicles, especially utilizing temporally sparse LiDAR frames. However, conventional explicit representations remain a significant bottleneck towards representing the reconstructed and synthetic scenes at unlimited resolution. Although the recently developed neural radiance fields (NeRF) have shown compelling results in implicit representations, the problem of large-scale 3D scene reconstruction and novel view synthesis using sparse LiDAR frames remains unexplored. To bridge this gap, we propose a 3D scene reconstruction and novel view synthesis framework called parent-child neural radiance field (PC-NeRF). Based on its two modules, parent NeRF and child NeRF, the framework implements hierarchical spatial partitioning and multi-level scene representation, including scene, segment, and point levels. The multi-level scene representation enhances the efficient utilization of sparse LiDAR point cloud data and enables the rapid acquisition of an approximate volumetric scene representation. With extensive experiments, PC-NeRF is proven to achieve high-precision novel LiDAR view synthesis and 3D reconstruction in large-scale scenes. Moreover, PC-NeRF can effectively handle situations with sparse LiDAR frames and demonstrate high deployment efficiency with limited training epochs. Our approach implementation and the pre-trained models are available at https://github.com/biter0088/pc-nerf.
For safe operation, autonomous vehicles have to obey traffic rules that are set forth in legal documents formulated in natural language. Temporal logic is a suitable concept to formalize such traffic rules. Still, temporal logic rules often result in constraints that are hard to solve using optimization-based motion planners. Reinforcement learning (RL) is a promising method to find motion plans for autonomous vehicles. However, vanilla RL algorithms are based on random exploration and do not automatically comply with traffic rules. Our approach accomplishes guaranteed rule-compliance by integrating temporal logic specifications into RL. Specifically, we consider the application of vessels on the open sea, which must adhere to the Convention on the International Regulations for Preventing Collisions at Sea (COLREGS). To efficiently synthesize rule-compliant actions, we combine predicates based on set-based prediction with a statechart representing our formalized rules and their priorities. Action masking then restricts the RL agent to this set of verified rule-compliant actions. In numerical evaluations on critical maritime traffic situations, our agent always complies with the formalized legal rules and never collides while achieving a high goal-reaching rate during training and deployment. In contrast, vanilla and traffic rule-informed RL agents frequently violate traffic rules and collide even after training.
This paper explores the role and challenges of Artificial Intelligence (AI) algorithms, specifically AI-based software elements, in autonomous driving systems. These AI systems are fundamental in executing real-time critical functions in complex and high-dimensional environments. They handle vital tasks like multi-modal perception, cognition, and decision-making tasks such as motion planning, lane keeping, and emergency braking. A primary concern relates to the ability (and necessity) of AI models to generalize beyond their initial training data. This generalization issue becomes evident in real-time scenarios, where models frequently encounter inputs not represented in their training or validation data. In such cases, AI systems must still function effectively despite facing distributional or domain shifts. This paper investigates the risk associated with overconfident AI models in safety-critical applications like autonomous driving. To mitigate these risks, methods for training AI models that help maintain performance without overconfidence are proposed. This involves implementing certainty reporting architectures and ensuring diverse training data. While various distribution-based methods exist to provide safety mechanisms for AI models, there is a noted lack of systematic assessment of these methods, especially in the context of safety-critical automotive applications. Many methods in the literature do not adapt well to the quick response times required in safety-critical edge applications. This paper reviews these methods, discusses their suitability for safety-critical applications, and highlights their strengths and limitations. The paper also proposes potential improvements to enhance the safety and reliability of AI algorithms in autonomous vehicles in the context of rapid and accurate decision-making processes.
Ensuring the robustness of lane detection systems is essential for the reliability of autonomous vehicles, particularly in the face of diverse weather conditions. While numerous algorithms have been proposed, addressing challenges posed by varying weather remains an ongoing issue. Geometric-based lane detection methods, rooted in the inherent properties of road geometry, provide enhanced generalizability. However, these methods often require manual parameter tuning to accommodate it fluctuating illumination and weather conditions. Conversely, learning-based approaches, trained on pre-labeled datasets, excel in localizing intricate and curved lane configurations but grapple with the absence of diverse weather datasets. This paper introduces a promising hybrid approach that merges the strengths of both methodologies. A novel adaptive preprocessing method is proposed in this work. Utilizing a fuzzy inference system (FIS), the algorithm dynamically adjusts parameters in geometric-based image processing functions and enhances adaptability to diverse weather conditions. Notably, this preprocessing algorithm is designed to seamlessly integrate with all learning-based lane detection models. When implemented in conjunction with CNN-based models, the hybrid approach demonstrates commendable generalizability across weather conditions and adaptability to complex lane configurations. Rigorous testing on datasets featuring challenging weather conditions showcases the proposed method's significant improvements over existing models, underscoring its efficacy in addressing the persistent challenges associated with lane detection in adverse weather scenarios.
This work explores the zero-shot adaptation capability of semantic skills, semantically interpretable experts' behavior patterns, in cross-domain settings, where a user input in interleaved multi-modal snippets can prompt a new long-horizon task for different domains. In these cross-domain settings, we present a semantic skill translator framework SemTra which utilizes a set of multi-modal models to extract skills from the snippets, and leverages the reasoning capabilities of a pretrained language model to adapt these extracted skills to the target domain. The framework employs a two-level hierarchy for adaptation: task adaptation and skill adaptation. During task adaptation, seq-to-seq translation by the language model transforms the extracted skills into a semantic skill sequence, which is tailored to fit the cross-domain contexts. Skill adaptation focuses on optimizing each semantic skill for the target domain context, through parametric instantiations that are facilitated by language prompting and contrastive learning-based context inferences. This hierarchical adaptation empowers the framework to not only infer a complex task specification in one-shot from the interleaved multi-modal snippets, but also adapt it to new domains with zero-shot learning abilities. We evaluate our framework with Meta-World, Franka Kitchen, RLBench, and CARLA environments. The results clarify the framework's superiority in performing long-horizon tasks and adapting to different domains, showing its broad applicability in practical use cases, such as cognitive robots interpreting abstract instructions and autonomous vehicles operating under varied configurations.
This research explores the integration of language embeddings for active learning in autonomous driving datasets, with a focus on novelty detection. Novelty arises from unexpected scenarios that autonomous vehicles struggle to navigate, necessitating higher-level reasoning abilities. Our proposed method employs language-based representations to identify novel scenes, emphasizing the dual purpose of safety takeover responses and active learning. The research presents a clustering experiment using Contrastive Language-Image Pretrained (CLIP) embeddings to organize datasets and detect novelties. We find that the proposed algorithm effectively isolates novel scenes from a collection of subsets derived from two real-world driving datasets, one vehicle-mounted and one infrastructure-mounted. From the generated clusters, we further present methods for generating textual explanations of elements which differentiate scenes classified as novel from other scenes in the data pool, presenting qualitative examples from the clustered results. Our results demonstrate the effectiveness of language-driven embeddings in identifying novel elements and generating explanations of data, and we further discuss potential applications in safe takeovers, data curation, and multi-task active learning.