Existing traffic simulation models often fall short in capturing the intricacies of real-world scenarios, particularly the interactive behaviors among multiple traffic participants, thereby limiting their utility in the evaluation and validation of autonomous driving systems. We introduce Versatile Behavior Diffusion (VBD), a novel traffic scenario generation framework based on diffusion generative models that synthesizes scene-consistent, realistic, and controllable multi-agent interactions. VBD achieves strong performance in closed-loop traffic simulation, generating scene-consistent agent behaviors that reflect complex agent interactions. A key capability of VBD is inference-time scenario editing through multi-step refinement, guided by behavior priors and model-based optimization objectives, enabling flexible and controllable behavior generation. Despite being trained on real-world traffic datasets with only normal conditions, we introduce conflict-prior and game-theoretic guidance approaches. These approaches enable the generation of interactive, customizable, or long-tail safety-critical scenarios, which are essential for comprehensive testing and validation of autonomous driving systems. Extensive experiments validate the effectiveness and versatility of VBD and highlight its promise as a foundational tool for advancing traffic simulation and autonomous vehicle development. Project website:https://sites.google.com/view/versatile-behavior-diffusion

The emerging connected and automated vehicle (CAV) technologies present opportunities to improve traffic safety, economy, and efficiency. However, the diverse uncontrollable human-driven vehicles (HDVs) will continue to predominate traffic for a long time, resulting in coexisting CAVs and HDVs in the form of mixed vehicle platoons. This study proposes a mixed vehicle platoon forming method based on a two-stage control framework to adapt to dynamic mixed traffic environments. The platoon formation generation stage creates feasible formation (i.e., a spatially coordinated mix of CAVs and HDVs ensuring safe and efficient platoon control) appropriate for mixed traffic based on the empirical formation method. The multiagent reinforcement learning is used in the second stage for realizing the platoon forming control safely and efficiently with the guidance of feasible formation. Finally, extensive simulations are conducted using the Highway-env simulator to evaluate the effectiveness of the proposed method. The results demonstrate that the proposed method can effectively control CAVs in conjunction with HDVs to form a mixed vehicle platoon, achieving an average energy efficiency improvement of up to 10.69% and a reduction in travel time by up to 2.73% compared to benchmark strategies.

We study constrained reinforcement learning (CRL) from a novel perspective by setting constraints directly on state density functions, rather than the value functions considered by previous works. State density has a clear physical and mathematical interpretation, and is able to express a wide variety of constraints such as resource limits and safety requirements. Density constraints can also avoid the time-consuming process of designing and tuning cost functions required by value function-based constraints to encode system specifications. We leverage the duality between density functions and Q functions to develop an effective algorithm to solve the density constrained RL problem optimally and the constrains are guaranteed to be satisfied. We prove that the proposed algorithm converges to a near-optimal solution with a bounded error even when the policy update is imperfect. We use a set of comprehensive experiments to demonstrate the advantages of our approach over state-of-the-art CRL methods, with a wide range of density constrained tasks as well as standard CRL benchmarks such as Safety-Gym.

This paper proposes a data-driven method for powered prosthesis control that achieves stable walking without the need for additional sensors on the human. The key idea is to extract the nominal gait and the human interaction information from motion capture data, and reconstruct the walking behavior with a dynamic model of the human-prosthesis system. The walking behavior of a human wearing a powered prosthesis is obtained through motion capture, which yields the limb and joint trajectories. Then a nominal trajectory is obtained by solving a gait optimization problem designed to reconstruct the walking behavior observed by motion capture. Moreover, the interaction force profiles between the human and the prosthesis are recovered by simulating the model following the recorded gaits, which are then used to construct a force tube that covers all the interaction force profiles. Finally, a robust Control Lyapunov Function (CLF) Quadratic Programming (QP) controller is designed to guarantee the convergence to the nominal trajectory under all possible interaction forces within the tube. Simulation results show this controller's improved tracking performance with a perturbed force profile compared to other control methods with less model information.