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.

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.

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.

We derive optimal control policies for a Connected Automated Vehicle (CAV) cooperating with neighboring CAVs in order to implement a lane change maneuver consisting of a longitudinal phase where the CAV properly positions itself relative to the cooperating neighbors and a lateral phase where it safely changes lanes. For the first phase, we optimize the maneuver time subject to safety constraints and subsequently minimize the associated surrogate energy consumption of all cooperating vehicles in this maneuver. For the second phase, we jointly optimize time and energy approximation and provide three different solution methods including a real-time approach based on Control Barrier Functions (CBFs). We prove structural properties of the optimal policies which simplify the solution derivations and, in the case of the longitudinal maneuver, lead to analytical optimal control expressions. The solutions, when they exist, are guaranteed to satisfy safety constraints for all vehicles involved in the maneuver. Simulation results where the controllers are implemented show their effectiveness in terms of significant performance improvements compared to maneuvers performed by human-driven vehicles.

Channel modeling is essential for design and performance evaluation of numerous protocols in vehicular networks. In this paper, we study and provide results for large- and small-scale modeling of communication channel in dense vehicular networks. We first propose an approach to remove the effect of fading on deterministic part of the large-scale model and verify its accuracy using a single transmitter-receiver scenario. Two-ray model is then utilized for path-loss characterization and its parameters are derived from the empirical data based on a newly proposed method. Afterward, we use α -μ distribution to model the fading behavior of vehicular networks for the first time, and validate its precision by Kolmogorov-Smirnov(K-S) goodness-of-fit test. To this end, the significantly better performance of utilizing α - μ distribution over the most adopted fading distribution in the vehicular channels literature, i.e., Nakagami-m, in terms of passing K-S test has been investigated and statistically verified in this paper. A large received signal strength indicator (RSSI) data set from a measurement campaign is used to evaluate our claims. Moreover, the whole model is implemented in a reliable discrete event network simulator which is widely used in the academic and industrial research for network analysis, i.e., network simulator-3 (ns-3), to show the outcome of the proposed model in the presence of upper layer network protocols.

Scalability is one of the major issues for real- world Vehicle-to-Vehicle network realization. To tackle this challenge, a stochastic hybrid modeling framework based on a non-parametric Bayesian inference method, i.e., hierarchical Dirichlet process (HDP), is investigated in this paper. This framework is able to jointly model driver/vehicle behavior through forecasting the vehicle dynamical time-series. This modeling framework could be merged with the notion of model-based information networking, which is recently proposed in the vehicular literature, to overcome the scalability challenges in dense vehicular networks via broadcasting the behavioral models instead of raw information dissemination. This modeling approach has been applied on several scenarios from the realistic Safety Pilot Model Deployment (SPMD) driving data set and the results show a higher performance of this model in comparison with the zero-hold method as the baseline.

Heterogeneous nature of the vehicular networks, which results from the co-existence of human-driven, semi-automated, and fully autonomous vehicles, is a challenging phenomenon toward the realization of the intelligent transportation systems with an acceptable level of safety, comfort, and efficiency. Safety applications highly suffer from communication resource limitations, specifically in dense and congested vehicular networks. The idea of model-based communication (MBC) has been recently proposed to address this issue. In this work, we propose Gaussian Process based Stochastic Hybrid System with Cumulative Relevant History (CRH-GP-SHS) framework, which is a hierarchical stochastic hybrid modeling structure, built upon a non-parametric Bayesian inference method, i.e. Gaussian processes. This framework is proposed in order to be employed within the MBC context to jointly model driver/vehicle behavior as a stochastic object. Non-parametric Bayesian methods relieve the limitations imposed by non-evolutionary model structures and enable the proposed framework to properly capture different stochastic behaviors. The performance of the proposed CRH-GP-SHS framework at the inter-mode level has been evaluated over a set of realistic lane change maneuvers from the NGSIM-US101 dataset. The results show a noticeable performance improvement for GP in comparison to the baseline constant speed model, specifically in critical situations such as highly congested networks. Moreover, an augmented model has also been proposed which is a composition of GP and constant speed models and capable of capturing the driver behavior under various network reliability conditions.

Forward Collision Warning (FCW) is a promising Advanced Driver Assistance System (ADAS) to mitigate rear-end collisions. The deterministic FCW approaches may occasionally lead to the issuance of annoying false warnings, as they cannot be individualized for different drivers. This application oversight, which may cause the driver to deactivate the system, has been tackled with some adaptive methods. However, driver distraction, which is one of the most influential driver-specific factors on FCW warnings acceptability, has not been considered yet and is analyzed in this paper for the first time. Specifically, the adaptive FCW method proposed in this paper generates the warnings by continuously comparing Time Headway with a flexible threshold. The core of the proposed threshold updating mechanism is a real-time monitoring of the driver reactions against the previously generated warnings using the available indicators such as braking history. This method considers the driver distraction in parallel to fine-tune the calculated threshold in accordance with driver cognitive state. In order to incorporate the driver distraction in the system framework, a learning-based approach is designed which continuously estimates driver distraction by the virtue of different available Controller Area Network (CAN) bus time series, such as throttle pedal position, velocity, acceleration, and yaw rate. Neural network, as a widely adopted classification method, is nominated to detect driver distraction. The framework performance is evaluated over two realistic driving datasets. An approximately 80% false warning reduction is observed in analyzed safe scenarios, while no critical warning is missed in the dangerous ones.