Personalized Autonomous Driving via Optimal Control with Clearance Constraints from Questionnaires

TL;DR

This work tackles the challenge of aligning autonomous driving trajectories with individual user comfort by explicitly encoding user preferences as clearance constraints. It introduces a questionnaire-driven preference space and a three-stage planning pipeline that decomposes the original constrained optimal control problem into scenario-specific subproblems solved in parallel, followed by selection using the original cost. The method enables direct, quantitative measurement of preference alignment and demonstrates improved adherence to user-specified clearances over preference-agnostic baselines in simulations across driving styles. The approach offers real-time feasibility and a path toward context-aware preference handling while maintaining safety constraints.

Abstract

Driving without considering the preferred separation distance from surrounding vehicles may cause discomfort for users. To address this limitation, we propose a planning framework that explicitly incorporates user preferences regarding the desired level of safe clearance from surrounding vehicles. We design a questionnaire purposefully tailored to capture user preferences relevant to our framework, while minimizing unnecessary questions. Specifically, the questionnaire considers various interaction-relevant factors, including the surrounding vehicle's size, speed, position, and maneuvers of surrounding vehicles, as well as the maneuvers of the ego vehicle. The response indicates the user-preferred clearance for the scenario defined by the question and is incorporated as constraints in the optimal control problem. However, it is impractical to account for all possible scenarios that may arise in a driving environment within a single optimal control problem, as the resulting computational complexity renders real-time implementation infeasible. To overcome this limitation, we approximate the original problem by decomposing it into multiple subproblems, each dealing with one fixed scenario. We then solve these subproblems in parallel and select one using the cost function from the original problem. To validate our work, we conduct simulations using different user responses to the questionnaire. We assess how effectively our planner reflects user preferences compared to preference-agnostic baseline planners by measuring preference alignment.

Figures (6)

• Figure 1: Our framework consists of three stages, illustrated by the magenta, cyan, and orange shaded regions, respectively. The first stage (questionnaire stage) collects the user-preferred clearance margin through a questionnaire. The second stage (parallel trajectory optimization stage) takes the questionnaire responses and the current driving scenario as inputs, then decomposes the original problem into scenario-specific subproblems. Finally, in the third stage (selection stage), these subproblems are solved in parallel, and one is selected using the cost function of the original problem.
• Figure 2: The $x$- and $y$-coordinates are equal to the longitudinal and lateral coordinates, respectively, because the Frenet frame represents curved roads as straight werling2010optimal. The abbreviations are summarized in Table \ref{['tab:abb']}.
• Figure 3: An example of a question in the questionnaire to address the single-vehicle interactions.
• Figure 4: The red and blue boxes are the target vehicle and EC, respectively. The orange and black dashed lines mean the predicted trajectory of target vehicles and the optimized trajectory of EC, respectively, and the light blue and green lines in (c) and (d) mean the lower and upper bounds of $\mathcal{S}_\phi$. The blue point in (c) and (d) represents the intersection point between the lower and upper bounds of $\mathcal{S}_\phi$. The lines with various colors in (a) and (c) denote the trajectory samples. The trajectory samples in (c) and the optimized trajectories in (d) are restricted in $\mathcal{S}_\phi$ to reflect the user-preferred clearances. When $\phi$ = RLC ahead of RLLC in (c), the current position of EC does not belong to $\mathcal{S}_\phi$; thus, there is no solution.
• Figure 5: The red and blue boxes, the orange and black dashed lines, and the light blue and green lines are the same as in Fig. \ref{['fig:long-term_comparison']}. (a) and (b) depict the solution of the subproblem for overtaking. The RLC ahead of RLLC in (a) does not have a feasible solution because the vehicle is not within $\mathcal{S}_\phi$. In contrast, the RLC ahead of RLAC in (b) has a feasible solution.