A Survey of Motion Planning and Control Techniques for Self-Driving Urban Vehicles

Analysis

Why This Paper Matters

Self-driving vehicles promise to transform mobility by improving safety, accessibility, efficiency, and convenience. Central to this promise is the ability to plan safe motions through dynamic urban environments shared with other vehicles and pedestrians, and to execute these plans robustly via feedback control. This survey, published in IEEE Transactions on Intelligent Vehicles in 2016, provides a timely and comprehensive overview of the state of the art in motion planning and control for self-driving urban vehicles. With over 2,500 citations, it has become a key reference in the autonomous driving community.

The paper addresses the critical need for a systematic comparison of planning and control techniques, which vary widely in their underlying mobility models, assumptions about environmental structure, and computational requirements. By offering a side-by-side comparison, the survey helps researchers and practitioners gain insight into the strengths and limitations of different approaches, thereby assisting with system-level design choices. This is particularly valuable in a field where safety-critical decisions must be made under uncertainty and real-time constraints.

Given the rapid progress in autonomous driving, this survey serves as a foundational document that captures the landscape of planning and control methods as of 2016. It highlights the diversity of solutions and the trade-offs involved, setting the stage for future research and development.

Technical Contributions

• Comprehensive Review: The paper surveys a broad selection of motion planning and control algorithms specifically tailored for urban self-driving scenarios.
• Comparative Framework: It introduces a comparison framework based on three key dimensions: the vehicle mobility model used, assumptions on the structure of the environment, and computational requirements.
• Effectiveness Discussion: For each reviewed technique, the paper discusses its effectiveness and limitations, providing practical insights for system designers.
• Identification of Safety-Critical Tasks: The survey explicitly identifies safety-critical tasks such as motion planning in dynamic environments and robust feedback control, emphasizing their importance.
• Guidance for System Design: By juxtaposing different approaches, the paper assists in making informed system-level design choices, bridging the gap between theory and practice.

Results

As a survey paper, it does not present new experimental results or quantitative metrics. Instead, its "results" are the comparative analysis and synthesized insights derived from the literature. The paper successfully categorizes and contrasts various planning and control techniques, revealing trade-offs between computational efficiency, model complexity, and environmental assumptions. It highlights that no single approach dominates all scenarios; rather, the choice depends on the specific requirements and constraints of the application. The side-by-side comparison enables readers to understand the relative advantages and disadvantages of methods such as graph-based planning, sampling-based planning, and reactive control strategies.

Significance

The survey's significance lies in its role as a foundational reference that consolidates knowledge in a rapidly evolving field. It provides a structured overview that helps new researchers quickly grasp the landscape and aids experienced practitioners in evaluating design alternatives. By emphasizing the importance of matching algorithm choices to specific urban driving challenges, the paper promotes a more thoughtful and systematic approach to autonomous vehicle development. Its high citation count attests to its impact and utility. Moreover, the paper's identification of safety-critical tasks and the need for robust feedback control underscores the challenges that remain in achieving fully autonomous urban driving, guiding future research directions. Overall, this survey has contributed to shaping the discourse on motion planning and control for self-driving vehicles and continues to be a valuable resource for the community.