Personalized Autonomous Driving Via Optimal Control with Clearance Constraints from Questionnaires
YongJae Lim, Dabin Kim, H. Jin Kim
AI summary
Problem
Most autonomous planners ignore individual user preferences for safe clearance distances, causing psychological discomfort and reduced trust. Existing data-driven approaches struggle with dataset alignment and real-time computational feasibility.
Approach
The authors design a concise questionnaire to capture user-preferred clearance margins for specific driving scenarios, then encode these responses as explicit constraints in an optimal control problem. To ensure real-time performance, the computationally heavy planning problem is decomposed into parallel scenario-specific subproblems that are solved and ranked by a cost function.
Key results
- Novel framework explicitly integrating user-preferred clearance as optimal control constraints
- Systematically designed questionnaire capturing scenario-specific clearance preferences with minimal items
- Parallel decomposition method enabling real-time trajectory optimization across multiple scenarios
- Simulation validation demonstrating high preference alignment with diverse driver types while maintaining safety
Why it matters
It bridges the gap between personalized user comfort and computationally feasible autonomous planning, making driving systems more trustworthy and adaptable to individual drivers.
Abstract
Driving without considering the preferred separa- tion distance from surrounding vehicles may cause discomfort for users. To address this limitation, we propose a planning framework that explicitly incorporates user preferences regard- ing 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 re- flects user preferences compared to preference-agnostic baseline planners by measuring preference alignment.