In social robot navigation, traditional metrics like proxemics and behavior naturalness emphasize human comfort and adherence to social norms but often fail to capture an agent's autonomy and adaptability in dynamic environments. This paper introduces human empowerment, an information-theoretic concept that measures a human's ability to influence their future states and observe those changes, as a complementary metric for evaluating social compliance. This metric reveals how robot navigation policies can indirectly impact human empowerment. We present a framework that integrates human empowerment into the evaluation of social performance in navigation tasks. Through numerical simulations, we demonstrate that human empowerment as a metric not only aligns with intuitive social behavior, but also shows statistically significant differences across various robot navigation policies. These results provide a deeper understanding of how different policies affect social compliance, highlighting the potential of human empowerment as a complementary metric for future research in social navigation.

Multi-agent reinforcement learning (MARL) has achieved significant progress in large-scale traffic control, autonomous vehicles, and robotics. Drawing inspiration from biological systems where roles naturally emerge to enable coordination, role-based MARL methods have been proposed to enhance cooperation learning for complex tasks. However, existing methods exclusively derive roles from an agent’s past experience during training, neglecting their influence on its future trajectories. This paper introduces a key insight: an agent’s role should shape its future behavior to enable effective coordination. Hence, we propose Role Discovery and Diversity through Dynamics Models (R3DM), a novel role-based MARL framework that learns emergent roles by maximizing the mutual information between agents’ roles, observed trajectories, and expected future behaviors. R3DM optimizes the proposed objective through contrastive learning on past trajectories to first derive intermediate roles that shape intrinsic rewards to promote diversity in future behaviors across different roles through a learned dynamics model. Benchmarking on SMAC and SMACv2 environments demonstrates that R3DM outperforms state-of-the-art MARL approaches, improving multi-agent coordination to increase win rates by up to 20%. The code is available at https://github.com/UTAustin-SwarmLab/R3DM.

In this paper, we address the challenges of limited interpretability and scalability in traditional trajectory prediction models for autonomous driving decision-making. We present the Dynamic Insertable Intention Interval framework (DI3), which introduces a novel representation of driving intentions by accounting for dynamic interactions with the surrounding environment. Our hierarchical approach integrates intention queries within a motion decoder, enabling the generation of multimodal predictions that closely replicate human driving behavior. Through comprehensive experiments on the highway on-ramp merging scenario using the exiD dataset, we demonstrate that DI3 enhances trajectory prediction accuracy and reduces joint prediction overlap rates compared to the Motion Transformer (MTR) baseline, demonstrating its effectiveness in high-interaction scenarios. Our work lays the foundation for more reliable and interpretable prediction models that is valuable for decision-making in autonomous driving applications.

Merging into dense highway traffic for an autonomous vehicle is a complex decision-making task, wherein the vehicle must identify a potential gap and coordinate with surrounding human drivers, each of whom may exhibit diverse driving behaviors. Many existing methods consider other drivers to be dynamic obstacles and, as a result, they are incapable of capturing the full intent of the human drivers through this passive planning. In this paper, we propose a novel dual control framework based on Model Predictive Path-Integral control to generate interactive trajectories. This framework incorporates a Bayesian inference approach to actively learn the agents’ parameters, i.e., other drivers’ model parameters. The proposed framework employs a sampling-based approach that is suitable for real-time implementation through the utilization of GPUs. We illustrate the effectiveness of our proposed methodology through comprehensive numerical simulations conducted in both high and low-fidelity simulation scenarios focusing on autonomous on-ramp merging.

In this paper, we develop a control framework for the coordination of multiple robots as they navigate through crowded environments. Our framework comprises of a local model predictive control (MPC) for each robot and a social long short-term memory model that forecasts pedestrians’ trajectories. We formulate the local MPC formulation for each individual robot that includes both individual and shared objectives, in which the latter encourages the emergence of coordination among robots. Next, we consider the multi-robot navigation and human-robot interaction, respectively, as a potential game and a two-player game, then employ an iterative best response approach to solve the resulting optimization problems in a centralized and distributed fashion. Finally, we demonstrate the effectiveness of coordination among robots in simulated crowd navigation.

Navigating a robot among a crowd has received increasing attention from researchers over the last few decades, resulting in the emergence of numerous approaches aimed at addressing the problem of social navigation to date. Our proposed approach couples agent motion prediction and planning to avoid the freezing robot problem while simultaneously capturing multi-agent social interactions by utilizing a state-of-the-art trajectory prediction model i.e., social long short-term memory model (Social-LSTM). Leveraging the output of Social-LSTM for the prediction of future trajectories of pedestrians at each time-step given the robot’s possible future actions, our framework computes the optimal control action using Model Predictive Control (MPC) for the robot to navigate among pedestrians. We demonstrate the effectiveness of our proposed approach in multiple scenarios of simulated social navigation and compare it against several state-of-the-art reinforcement learning-based methods.

Enhancing simulation environments to replicate real-world driver behavior is essential for developing Autonomous Vehicle technology. While some previous works have studied the yielding reaction of lag vehicles in response to a merging car at highway on-ramps, the possible lane-change reaction of the lag car has not been widely studied. In this work we aim to improve the simulation of the highway merge scenario by including the lane-change reaction in addition to yielding behavior of main-lane lag vehicles, and we evaluate two different models for their ability to capture this reactive lane-change behavior. To tune the payoff functions of these models, a novel naturalistic dataset was collected on U.S. highways that provided several hours of merge-specific data to learn the lane change behavior of U.S. drivers. To make sure that we are collecting a representative set of different U.S. highway geometries in our data, we surveyed 50,000 U.S. highway on-ramps and then selected eight representative sites. The data were collected using roadside-mounted lidar sensors to capture various merge driver interactions. The models were demonstrated to be configurable for both keep-straight and lane-change behavior. The models were finally integrated into a high-fidelity simulation environment and confirmed to have adequate computation time efficiency for use in large-scale simulations to support autonomous vehicle development.

Multi-Agent Reinforcement Learning (MARL) methods have shown promise in enabling agents to learn a shared communication protocol from scratch and accomplish challenging team tasks. However, the learned language is usually not interpretable to humans or other agents not co-trained together, limiting its applicability in ad-hoc teamwork scenarios. In this work, we propose a novel computational pipeline that aligns the communication space between MARL agents with an embedding space of human natural language by grounding agent communications on synthetic data generated by embodied Large Language Models (LLMs) in interactive teamwork scenarios. Our results demonstrate that introducing language grounding not only maintains task performance but also accelerates the emergence of communication. Furthermore, the learned communication protocols exhibit zero-shot generalization capabilities in ad-hoc teamwork scenarios with unseen teammates and novel task states. This work presents a significant step toward enabling effective communication and collaboration between artificial agents and humans in real-world teamwork settings.

Research in Cooperative Intersection Management (CIM), utilizing Vehicle-to-Everything (V2X) communication among Connected and/or Autonomous Vehicles (CAVs), is crucial for enhancing intersection safety and driving experience. CAVs can transceive basic and/or advanced safety information, thereby improving situational awareness at intersections. The focus of this study is on unsignalized intersections, particularly Stop Controlled-Intersections (SC-Is), where one of the main reasons involving crashes is the ambiguity among CAVs in SC-I crossing priority upon arriving at similar time intervals. Numerous studies have been performed on CIM for unsignalized intersections based on centralized and distributed systems in the presence and absence of Road-Side Unit (RSU), respectively. However, most of these studies are focused towards replacing SC-I where the scheduler provides spatio-temporal or sequence-based reservation to CAVs, or where it controls CAVs via kinematic commands. These methods cause CAVs to arrive at the intersection at non-conflicting times and cross without stopping. This logic is severely limited in real-world mixed traffic comprising human drivers where kinematic commands and other reservations cannot be implemented as intended. Thus, given the existence of SC-Is and mixed traffic, it is significant to develop CIM systems incorporating SC-I rules while assigning crossing priorities and resolving the related ambiguity. In this regard, we propose a distributed Automated Right-of-Way (AROW) algorithm for CIM to assign explicit SC-I crossing turns to CAVs and mitigate hazardous scenarios due to ambiguity towards crossing priority. The algorithm is validated with extensive experiments for its functionality, scalability, and robustness towards CAV non-compliance, and it outperforms the current solutions.

Advanced Driver Assistance Systems (ADAS) with proactive alerts have been used to increase driving safety. Such systems’ performance greatly depends on how accurately and quickly the risky situations and maneuvers are detected. Existing ADAS provide warnings based on the vehicle’s operational status, detection of environments, and the drivers’ overt actions (e.g., using turn signals or steering wheels), which may not give drivers as much as optimal time to react. In this paper, we proposed a spatio-temporal attention-based neural network to predict drivers’ lane-change intention by fusing the videos from both in-cabin and forward perspectives. The Convolutional Neural Network (CNN)-Recursive Neural Network (RNN) network architecture was leveraged to extract both the spatial and temporal information. On top of this network backbone structure, the feature maps from different time steps and perspectives were fused using multi-head self-attention at each resolution of the CNN. The proposed model was trained and evaluated using a processed subset of the MIT Advanced Vehicle Technology (MIT-AVT) dataset which contains synchronized CAN data, 11058-second videos from 3 different views, 548 lane-change events, and 274 non-lane-change events performed by 83 drivers. The results demonstrate that the model achieves 87% F1-score within the 1-second validation window and 70% F1-score within the 5-second validation window with real-time performance.

Efficient compression of correlated data is essential to minimize communication overload in multi-sensor networks. In such networks, each sensor independently compresses the data and transmits them to a central node. A decoder at the central node decompresses and passes the data to a pre-trained machine learning-based task model to generate the final output. Due to limited communication bandwidth, it is important for the compressor to learn only the features that are relevant to the task. Additionally, the final performance depends heavily on the total available bandwidth. In practice, it is common to encounter varying availability in bandwidth. Since higher bandwidth results in better performance, it is essential for the compressor to dynamically take advantage of the maximum available bandwidth at any instant. In this work, we propose a novel distributed compression framework composed of independent encoders and a joint decoder, which we call neural distributed principal component analysis (NDPCA). NDPCA flexibly compresses data from multiple sources to any available bandwidth with a single model, reducing compute and storage overhead. NDPCA achieves this by learning low-rank task representations and efficiently distributing bandwidth among sensors, thus providing a graceful trade-off between performance and bandwidth. Experiments show that NDPCA improves the success rate of multi-view robotic arm manipulation by 9% and the accuracy of object detection tasks on satellite imagery by 14% compared to an autoencoder with uniform bandwidth allocation.

Vehicle-to-Vehicle (V2V) communication systems have an eminence potential to improve road safety and optimize traffic flow by broadcasting Basic Safety Messages (BSMs). Dedicated Short-Range Communication (DSRC) and LTE Vehicle-to-Everything (V2X) are two candidate technologies to enable V2V communication. DSRC relies on the IEEE 802.11p standard for its PHY and MAC layer while LTE-V2X is based on 3GPP’s Release 14 and operates in a distributed manner in the absence of cellular infrastructure. There has been considerable debate over the relative advantages and disadvantages of DSRC and LTE-V2X, aiming to answer the fundamental question of which technology is most effective in real-world scenarios for various road safety and traffic efficiency applications. In this paper, we present a comprehensive survey of these two technologies (i.e., DSRC and LTE-V2X) and related works. More specifically, we study the PHY and MAC layer of both technologies in the survey study and compare the PHY layer performance using a variety of field tests. First, we provide a summary of each technology and highlight the limitations of each in supporting V2X applications. Then, we examine their performance based on different metrics.

This paper offers a technique for estimating collision risk for automated ground vehicles engaged in cooperative sensing. The technique allows quantification of (i) risk reduced due to cooperation, and (ii) the increased accuracy of risk assessment due to cooperation. If either is significant, cooperation can be viewed as a desirable practice for meeting the stringent risk budget of increasingly automated vehicles; if not, then cooperation-with its various drawbacks-need not be pursued. Collision risk is evaluated over an ego vehicle's trajectory based on a dynamic probabilistic occupancy map and a loss function that maps collision-relevant state information to a cost metric. The risk evaluation framework is demonstrated using real data captured from two cooperating vehicles traversing an urban intersection.

Millimeter wave (mmWave) has the potential to offer high data rates for vehicle-to-everything (V2X) communication. In this paper, we provide an introduction to important use cases of V2X as they pertain to fifth generation (5G) communication networks. As 5G technology is still evolving to support vehicles, and mmWave is reflected and blocked by vehicles, it remains unclear if the target rates for the use cases can be achieved. Motivated by the different data rate requirements, we introduce a methodology for evaluating rates in 5G mmWave V2X scenarios. Our approach leverages available city CAD models, realistic traffic simulators, and industry standard ray tracing tools to allow site-specific propagation evaluation. This approach may be used to devise insight into the role of traffic density, antenna array placement, and base station density in important urban propagation settings. Results are provided that highlight the application to develop a rate map for an urban intersection. They show that rate increases in dense deployments by more than ten percent per base station, but only decreases about one percent when going from light to heavy traffic.

Advanced communication technology is the enabling factor for distributed sensing and control in smart grid. The performance of communication has a significant effect on the performance of the controllers that manage a power system. This effect is more profound when transient level behavior and critical applications are concerned. In these cases, an important issue is to design control-aware communication strategies for utilizing available communication technologies. Such strategies should describe what needs to be communicated when and between which nodes. In this paper, an “on-demand” strategy is presented that describes how communication subsystems should be configured, almost agnostically to the underlying technologies, to achieve significant performance improvement for the application. The on-demand method relies on the concept of error-dependent communication for tracking dynamical systems over communication networks. The paper also introduces the design of an embedded communication simulator integrated with PSCAD for cosimulation of communication strategies/protocols and power system components.