H. Eric Tseng

Monimoy Bujarbaruah, Xiaojing Zhang, H. Eric Tseng et al.

This paper proposes an Adaptive Robust Model Predictive Control strategy for lateral control in lane keeping problems, where we continuously learn an unknown, but constant steering angle offset present in the steering system. Longitudinal velocity is assumed constant. The goal is to minimize the outputs, which are distance from lane center line and the steady state heading angle error, while satisfying respective safety constraints. We do not assume perfect knowledge of the vehicle lateral dynamics model and estimate and adapt in real-time the maximum possible bound of the steering angle offset from data using a robust Set Membership Method based approach. Our approach is even well-suited for scenarios with sharp curvatures on high speed, where obtaining a precise model bias for constrained control is difficult, but learning from data can be helpful. We ensure persistent feasibility using a switching strategy during change of lane curvature. The proposed methodology is general and can be applied to more complex vehicle dynamics problems.

Yue Guan, Anuradha M. Annaswamy, H. Eric Tseng

Cumulative Prospect Theory (CPT) is a modeling tool widely used in behavioral economics and cognitive psychology that captures subjective decision making of individuals under risk or uncertainty. In this paper, we propose a dynamic pricing strategy for Shared Mobility on Demand Services (SMoDSs) using a passenger behavioral model based on CPT. This dynamic pricing strategy together with dynamic routing via a constrained optimization algorithm that we have developed earlier, provide a complete solution customized for SMoDS of multi-passenger transportation. The basic principles of CPT and the derivation of the passenger behavioral model in the SMoDS context are described in detail. The implications of CPT on dynamic pricing of the SMoDS are delineated using computational experiments involving passenger preferences. These implications include interpretation of the classic fourfold pattern of risk attitudes, strong risk aversion over mixed prospects, and behavioral preferences of self reference. Overall, it is argued that the use of the CPT framework corresponds to a crucial building block in designing socio-technical systems by allowing quantification of subjective decision making under risk or uncertainty that is perceived to be otherwise qualitative.

Xiao Li, Kaiwen Liu, H. Eric Tseng et al.

Understanding the intention of vehicles in the surrounding traffic is crucial for an autonomous vehicle to successfully accomplish its driving tasks in complex traffic scenarios such as highway forced merging. In this paper, we consider a behavioral model that incorporates both social behaviors and personal objectives of the interacting drivers. Leveraging this model, we develop a receding-horizon control-based decision-making strategy, that estimates online the other drivers' intentions using Bayesian filtering and incorporates predictions of nearby vehicles' behaviors under uncertain intentions. The effectiveness of the proposed decision-making strategy is demonstrated and evaluated based on simulation studies in comparison with a game theoretic controller and a real-world traffic dataset.

Xiao Li, Kaiwen Liu, H. Eric Tseng et al.

Autonomous vehicles need to accomplish their tasks while interacting with human drivers in traffic. It is thus crucial to equip autonomous vehicles with artificial reasoning to better comprehend the intentions of the surrounding traffic, thereby facilitating the accomplishments of the tasks. In this work, we propose a behavioral model that encodes drivers' interacting intentions into latent social-psychological parameters. Leveraging a Bayesian filter, we develop a receding-horizon optimization-based controller for autonomous vehicle decision-making which accounts for the uncertainties in the interacting drivers' intentions. For online deployment, we design a neural network architecture based on the attention mechanism which imitates the behavioral model with online estimated parameter priors. We also propose a decision tree search algorithm to solve the decision-making problem online. The proposed behavioral model is then evaluated in terms of its capabilities for real-world trajectory prediction. We further conduct extensive evaluations of the proposed decision-making module, in forced highway merging scenarios, using both simulated environments and real-world traffic datasets. The results demonstrate that our algorithms can complete the forced merging tasks in various traffic conditions while ensuring driving safety.

Yutong Li, Nan Li, H. Eric Tseng et al.

The action governor is an add-on scheme to a nominal control loop that monitors and adjusts the control actions to enforce safety specifications expressed as pointwise-in-time state and control constraints. In this paper, we introduce the Robust Action Governor (RAG) for systems the dynamics of which can be represented using discrete-time Piecewise Affine (PWA) models with both parametric and additive uncertainties and subject to non-convex constraints. We develop the theoretical properties and computational approaches for the RAG. After that, we introduce the use of the RAG for realizing safe Reinforcement Learning (RL), i.e., ensuring all-time constraint satisfaction during online RL exploration-and-exploitation process. This development enables safe real-time evolution of the control policy and adaptation to changes in the operating environment and system parameters (due to aging, damage, etc.). We illustrate the effectiveness of the RAG in constraint enforcement and safe RL using the RAG by considering their applications to a soft-landing problem of a mass-spring-damper system.

Peiyuan Fang, Weiqi Zhang, Lu Xiong et al.

This paper introduces the Generalized Action Governor (AG), a supervisory scheme that augments a nominal closed-loop system with the capability to enforce state and input constraints through online action adjustment. We develop a generalized AG theory for discrete-time systems under bounded uncertainties, and relax the usual requirement of positive invariance to returnability of a safe set. Based on the theory, we present tailored AG design procedures for linear systems and for discrete systems with finite state and action spaces. We further study safe online learning enabled by the AG and present two safe learning strategies, namely safe Q-learning and safe data-driven Koopman operator-based control, both integrated with the AG to guarantee constraint satisfaction during learning. Numerical results illustrate the proposed methods.

Lu Wen, Songan Zhang, H. Eric Tseng et al.

Meta reinforcement learning (Meta RL) has been amply explored to quickly learn an unseen task by transferring previously learned knowledge from similar tasks. However, most state-of-the-art algorithms require the meta-training tasks to have a dense coverage on the task distribution and a great amount of data for each of them. In this paper, we propose MetaDreamer, a context-based Meta RL algorithm that requires less real training tasks and data by doing meta-imagination and MDP-imagination. We perform meta-imagination by interpolating on the learned latent context space with disentangled properties, as well as MDP-imagination through the generative world model where physical knowledge is added to plain VAE networks. Our experiments with various benchmarks show that MetaDreamer outperforms existing approaches in data efficiency and interpolated generalization.

Yaru Niu, Zhenlong Fang, Binghong Chen et al.

Humanoid robots promise general-purpose assistance, yet real-world humanoid loco-manipulation remains challenging because it requires whole-body stability, dexterous hands, and contact-aware perception under frequent contact changes. In this work, we study dexterous, contact-rich humanoid loco-manipulation. We first develop an RL-based whole-body controller that provides stable lower-body and torso execution during complex manipulation. Built on this controller, we develop a whole-body humanoid data collection system that combines VR-based teleoperation with human-to-humanoid motion mapping, enabling efficient collection of real-world demonstrations. We then propose Humanoid Transformer with Touch Dreaming (HTD), a multimodal encoder--decoder Transformer that models touch as a core modality alongside multi-view vision and proprioception. HTD is trained in a single stage with behavioral cloning augmented by touch dreaming: in addition to predicting action chunks, the policy predicts future hand-joint forces and future tactile latents, encouraging the shared Transformer trunk to learn contact-aware representations for dexterous interaction. Across five contact-rich tasks, Insert-T, Book Organization, Towel Folding, Cat Litter Scooping, and Tea Serving, HTD achieves a 90.9% relative improvement in average success rate over the stronger baseline. Ablation results further show that latent-space tactile prediction is more effective than raw tactile prediction, yielding a 30% relative gain in success rate. These results demonstrate that combining robust whole-body execution, scalable humanoid data collection, and predictive touch-centered learning enables versatile, high-dexterity humanoid manipulation in the real world. Project webpage: humanoid-touch-dream.github.io.

Hao Zhang, Yves Tseng, Ding Zhao et al.

Cooperative object transport in unstructured environments remains challenging for assistive humanoids because strong, time-varying interaction forces can make tracking-centric whole-body control unreliable, especially in close-contact support tasks. This paper proposes a bio-inspired, interaction-oriented whole-body control (IO-WBC) that functions as an artificial cerebellum - an adaptive motor agent that translates upstream (skill-level) commands into stable, physically consistent whole-body behavior under contact. This work structurally separates upper-body interaction execution from lower-body support control, enabling the robot to maintain balance while shaping force exchange in a tightly coupled robot-object system. A trajectory-optimized reference generator (RG) provides a kinematic prior, while a reinforcement learning (RL) policy governs body responses under heavy-load interactions and disturbances. The policy is trained in simulation with randomized payload mass/inertia and external perturbations, and deployed via asymmetric teacher-student distillation so that the student relies only on proprioceptive histories at runtime. Extensive experiments demonstrate that IO-WBC maintains stable whole-body behavior and physical interaction even when precise velocity tracking becomes infeasible, enabling compliant object transport across a wide range of scenarios.

Hao Zhang, Ding Zhao, H. Eric Tseng

Effective human-robot collaboration (HRC) requires translating high-level intent into contact-stable whole-body motion while continuously adapting to a human partner. Many vision-language-action (VLA) systems learn end-to-end mappings from observations and instructions to actions, but they often emphasize reactive (System 1-like) behavior and leave under-specified how sustained System 2-style deliberation can be integrated with reliable, low-latency continuous control. This gap is acute in multi-agent HRC, where long-horizon coordination decisions and physical execution must co-evolve under contact, feasibility, and safety constraints. We address this limitation with cognition-to-control (C2C), a three-layer hierarchy that makes the deliberation-to-control pathway explicit: (i) a VLM-based grounding layer that maintains persistent scene referents and infers embodiment-aware affordances/constraints; (ii) a deliberative skill/coordination layer-the System 2 core-that optimizes long-horizon skill choices and sequences under human-robot coupling via decentralized MARL cast as a Markov potential game with a shared potential encoding task progress; and (iii) a whole-body control layer that executes the selected skills at high frequency while enforcing kinematic/dynamic feasibility and contact stability. The deliberative layer is realized as a residual policy relative to a nominal controller, internalizing partner dynamics without explicit role assignment. Experiments on collaborative manipulation tasks show higher success and robustness than single-agent and end-to-end baselines, with stable coordination and emergent leader-follower behaviors.

Hao Zhang, Yaru Niu, Yikai Wang et al.

To improve generalization and resilience in human-robot collaboration (HRC), robots must handle the combinatorial diversity of human behaviors and contexts, motivating multi-agent reinforcement learning (MARL). However, inherent heterogeneity between robots and humans creates a rationality gap (RG) in the learning process-a variational mismatch between decentralized best-response dynamics and centralized cooperative ascent. The resulting learning problem is a general-sum differentiable game, so independent policy-gradient updates can oscillate or diverge without added structure. We propose heterogeneous-agent Lyapunov policy optimization (HALyPO), which establishes formal stability directly in the policy-parameter space by enforcing a per-step Lyapunov decrease condition on a parameter-space disagreement metric. Unlike Lyapunov-based safe RL, which targets state/trajectory constraints in constrained Markov decision processes, HALyPO uses Lyapunov certification to stabilize decentralized policy learning. HALyPO rectifies decentralized gradients via optimal quadratic projections, ensuring monotonic contraction of RG and enabling effective exploration of open-ended interaction spaces. Extensive simulations and real-world humanoid-robot experiments show that this certified stability improves generalization and robustness in collaborative corner cases.

Jianhua Wu, Bingzhao Gao, Jincheng Gao et al.

With the development of artificial intelligence and breakthroughs in deep learning, large-scale Foundation Models (FMs), such as GPT, Sora, etc., have achieved remarkable results in many fields including natural language processing and computer vision. The application of FMs in autonomous driving holds considerable promise. For example, they can contribute to enhancing scene understanding and reasoning. By pre-training on rich linguistic and visual data, FMs can understand and interpret various elements in a driving scene, and provide cognitive reasoning to give linguistic and action instructions for driving decisions and planning. Furthermore, FMs can augment data based on the understanding of driving scenarios to provide feasible scenes of those rare occurrences in the long tail distribution that are unlikely to be encountered during routine driving and data collection. The enhancement can subsequently lead to improvement in the accuracy and reliability of autonomous driving systems. Another testament to the potential of FMs' applications lies in World Models, exemplified by the DREAMER series, which showcases the ability to comprehend physical laws and dynamics. Learning from massive data under the paradigm of self-supervised learning, World Model can generate unseen yet plausible driving environments, facilitating the enhancement in the prediction of road users' behaviors and the off-line training of driving strategies. In this paper, we synthesize the applications and future trends of FMs in autonomous driving. By utilizing the powerful capabilities of FMs, we strive to tackle the potential issues stemming from the long-tail distribution in autonomous driving, consequently advancing overall safety in this domain.

Xiao Li, H. Eric Tseng, Anouck Girard et al.

Autonomous driving depends on perception systems to understand the environment and to inform downstream decision-making. While advanced perception systems utilizing black-box Deep Neural Networks (DNNs) demonstrate human-like comprehension, their unpredictable behavior and lack of interpretability may hinder their deployment in safety critical scenarios. In this paper, we develop an Ensemble of DNN regressors (Deep Ensemble) that generates predictions with quantification of prediction uncertainties. In the scenario of Adaptive Cruise Control (ACC), we employ the Deep Ensemble to estimate distance headway to the lead vehicle from RGB images and enable the downstream controller to account for the estimation uncertainty. We develop an adaptive cruise controller that utilizes Stochastic Model Predictive Control (MPC) with chance constraints to provide a probabilistic safety guarantee. We evaluate our ACC algorithm using a high-fidelity traffic simulator and a real-world traffic dataset and demonstrate the ability of the proposed approach to effect speed tracking and car following while maintaining a safe distance headway. The out-of-distribution scenarios are also examined.

Kaiwen Liu, Nan Li, H. Eric Tseng et al.

Merging is, in general, a challenging task for both human drivers and autonomous vehicles, especially in dense traffic, because the merging vehicle typically needs to interact with other vehicles to identify or create a gap and safely merge into. In this paper, we consider the problem of autonomous vehicle control for forced merge scenarios. We propose a novel game-theoretic controller, called the Leader-Follower Game Controller (LFGC), in which the interactions between the autonomous ego vehicle and other vehicles with a priori uncertain driving intentions is modeled as a partially observable leader-follower game. The LFGC estimates the other vehicles' intentions online based on observed trajectories, and then predicts their future trajectories and plans the ego vehicle's own trajectory using Model Predictive Control (MPC) to simultaneously achieve probabilistically guaranteed safety and merging objectives. To verify the performance of LFGC, we test it in simulations and with the NGSIM data, where the LFGC demonstrates a high success rate of 97.5% in merging.

Siddharth H. Nair, Vijay Govindarajan, Theresa Lin et al.

We propose a Stochastic MPC (SMPC) formulation for autonomous driving at traffic intersections which incorporates multi-modal predictions of surrounding vehicles for collision avoidance constraints. The multi-modal predictions are obtained with Gaussian Mixture Models (GMM) and constraints are formulated as chance-constraints. Our main theoretical contribution is a SMPC formulation that optimizes over a novel feedback policy class designed to exploit additional structure in the GMM predictions, and that is amenable to convex programming. The use of feedback policies for prediction is motivated by the need for reduced conservatism in handling multi-modal predictions of the surrounding vehicles, especially prevalent in traffic intersection scenarios. We evaluate our algorithm along axes of mobility, comfort, conservatism and computational efficiency at a simulated intersection in CARLA. Our simulations use a kinematic bicycle model and multimodal predictions trained on a subset of the Lyft Level 5 prediction dataset. To demonstrate the impact of optimizing over feedback policies, we compare our algorithm with two SMPC baselines that handle multi-modal collision avoidance chance constraints by optimizing over open-loop sequences.

Lu Wen, Songan Zhang, H. Eric Tseng et al.

Meta Reinforcement Learning (Meta-RL) has seen substantial advancements recently. In particular, off-policy methods were developed to improve the data efficiency of Meta-RL techniques. \textit{Probabilistic embeddings for actor-critic RL} (PEARL) is a leading approach for multi-MDP adaptation problems. A major drawback of many existing Meta-RL methods, including PEARL, is that they do not explicitly consider the safety of the prior policy when it is exposed to a new task for the first time. Safety is essential for many real-world applications, including field robots and Autonomous Vehicles (AVs). In this paper, we develop the PEARL PLUS (PEARL$^+$) algorithm, which optimizes the policy for both prior (pre-adaptation) safety and posterior (after-adaptation) performance. Building on top of PEARL, our proposed PEARL$^+$ algorithm introduces a prior regularization term in the reward function and a new Q-network for recovering the state-action value under prior context assumptions, to improve the robustness to task distribution shift and safety of the trained network exposed to a new task for the first time. The performance of PEARL$^+$ is validated by solving three safety-critical problems related to robots and AVs, including two MuJoCo benchmark problems. From the simulation experiments, we show that safety of the prior policy is significantly improved and more robust to task distribution shift compared to PEARL.

Songan Zhang, Lu Wen, Huei Peng et al.

It is essential for an automated vehicle in the field to perform discretionary lane changes with appropriate roadmanship - driving safely and efficiently without annoying or endangering other road users - under a wide range of traffic cultures and driving conditions. While deep reinforcement learning methods have excelled in recent years and been applied to automated vehicle driving policy, there are concerns about their capability to quickly adapt to unseen traffic with new environment dynamics. We formulate this challenge as a multi-Markov Decision Processes (MDPs) adaptation problem and developed Meta Reinforcement Learning (MRL) driving policies to showcase their quick learning capability. Two types of distribution variation in environments were designed and simulated to validate the fast adaptation capability of resulting MRL driving policies which significantly outperform a baseline RL.

Yutong Li, Nan Li, H. Eric Tseng et al.

Reinforcement Learning (RL) is essentially a trial-and-error learning procedure which may cause unsafe behavior during the exploration-and-exploitation process. This hinders the application of RL to real-world control problems, especially to those for safety-critical systems. In this paper, we introduce a framework for safe RL that is based on integration of a RL algorithm with an add-on safety supervision module, called the Robust Action Governor (RAG), which exploits set-theoretic techniques and online optimization to manage safety-related requirements during learning. We illustrate this proposed safe RL framework through an application to automotive adaptive cruise control.

Yutong Li, Nan Li, H. Eric Tseng et al.

We propose a game theoretic approach to address the problem of searching for available parking spots in a parking lot and picking the ``optimal'' one to park. The approach exploits limited information provided by the parking lot, i.e., its layout and the current number of cars in it. Considering the fact that such information is or can be easily made available for many structured parking lots, the proposed approach can be applicable without requiring major updates to existing parking facilities. For large parking lots, a sampling-based strategy is integrated with the proposed approach to overcome the associated computational challenge. The proposed approach is compared against a state-of-the-art heuristic-based parking spot search strategy in the literature through simulation studies and demonstrates its advantage in terms of achieving lower cost function values.

Songan Zhang, Huei Peng, Subramanya Nageshrao et al.

Deep reinforcement learning methods have been widely used in recent years for autonomous vehicle's decision-making. A key issue is that deep neural networks can be fragile to adversarial attacks or other unseen inputs. In this paper, we address the latter issue: we focus on generating socially acceptable perturbations (SAP), so that the autonomous vehicle (AV agent), instead of the challenging vehicle (attacker), is primarily responsible for the crash. In our process, one attacker is added to the environment and trained by deep reinforcement learning to generate the desired perturbation. The reward is designed so that the attacker aims to fail the AV agent in a socially acceptable way. After training the attacker, the agent policy is evaluated in both the original naturalistic environment and the environment with one attacker. The results show that the agent policy which is safe in the naturalistic environment has many crashes in the perturbed environment.

Ali Baheri, Subramanya Nageshrao, H. Eric Tseng et al.

In this paper, we present a safe deep reinforcement learning system for automated driving. The proposed framework leverages merits of both rule-based and learning-based approaches for safety assurance. Our safety system consists of two modules namely handcrafted safety and dynamically-learned safety. The handcrafted safety module is a heuristic safety rule based on common driving practice that ensure a minimum relative gap to a traffic vehicle. On the other hand, the dynamically-learned safety module is a data-driven safety rule that learns safety patterns from driving data. Specifically, the dynamically-leaned safety module incorporates a model lookahead beyond the immediate reward of reinforcement learning to predict safety longer into the future. If one of the future states leads to a near-miss or collision, then a negative reward will be assigned to the reward function to avoid collision and accelerate the learning process. We demonstrate the capability of the proposed framework in a simulation environment with varying traffic density. Our results show the superior capabilities of the policy enhanced with dynamically-learned safety module.