This framework introduces a consensus spatiotemporal safety barrier within a scenario tree structure to address potential hazards. Using consensus ADMM and a shared spatiotemporal safety barrier for each trajectory, the framework evaluates diverse risk configurations while enforcing motion consistency under perception uncertainty, such as sensor mis-detections. The framework is particularly effective in environments with dense obstacles in partially observable environments, enabling scalability to handle an increasing number of obstacles in large-scale, real-time optimization. We present the limitations of current parallel trajectory planning approaches, particularly their low accuracy and poor real-time performance.
One key underlying factor to the safety concern stems from uncertainties in both internal system models and external environments. [These uncertainties become critical in contingency scenarios, where potential risks cannot be predicted with certainty](https://iscicra25.github.io/papers/2025-Zheng-5_Towards_Real_time_Safe_Optim.pdf).
This research seamlessly integrates discrete decision-making maneuvers with continuous trajectory variables for safety-critical autonomous driving. The algorithm operates in real-time, optimizing trajectories of autonomous vehicles to ensure safety, stability, and proactive interaction with uncertain human-driven vehicles across various driving tasks, utilizing over-relaxed ADMM iterations. We provide a comprehensive theoretical analysis of safety and computational efficiency.
This research proposes a computationally-efficient spatiotemporal receding horizon control (ST-RHC) scheme to generate a safe, dynamically feasible, energy-efficient trajectory in control space, where different driving tasks in dense traffic can be achieved with high accuracy and safety in real time. The effectiveness of the proposed ST-RHC scheme is demonstrated through comprehensive comparisons with state-of-the-art algorithms on synthetic and real-world traffic datasets under dense traffic.
Present a real-time fail-operational controller for autonomous driving in the presence of time-varying environmental disturbances. This controller is designed to guide autonomous vehicles back to a predefined safe state asymptotically, while upholding task efficiency.
Present an integrated decision and trajectory planning approach for the autonomous vehicles to achieve high travel efficiency in dynamic and congested environments.
Present a real-time parallel trajectory optimization method for the autonomous vehicles to achieve high travel efficiency in dynamic and congested environments.
We propose a learning-based tracking control scheme based on a feedback linearization controller in which uncertain disturbances are approximated online using Gaussian Processes. Using the predicted distribution of disturbances given by GPs, a Control Lyapunov Function and Control Barrier Function based Quadratic Program is applied, with which probabilistic stability and safety are guaranteed.