Shared Autonomy for Proximal Teaching

2025-02-27

AI Summary

Existing AI-assisted instruction often oversimplifies learning, neglecting dynamic teacher-student interactions and individual learner variability. To address this, we propose Z-COACH—a novel pedagogical framework that integrates Vygotskian scaffolding into shared autonomy for high-skill domains such as professional racing. Z-COACH decomposes expertise into interpretable sub-skills and dynamically identifies each learner’s Zone of Proximal Development (ZPD) through behavioral evolution under semi-autonomous assistance. Technically, it unifies CARLA-based shared control, trajectory behavior analysis, sub-skill learnability assessment, and adaptive curriculum planning. A 50-participant user study demonstrates that Z-COACH outperforms baseline methods: lap times improve by 12.3%, control rationality increases by 28.6%, and motion smoothness significantly rises—validating shared autonomy’s dual capacity for real-time assistance and adaptive pedagogy.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: Behavior Learning & Control
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: The sharing economy

Abstract

Motor skill learning often requires experienced professionals who can provide personalized instruction. Unfortunately, the availability of high-quality training can be limited for specialized tasks, such as high performance racing. Several recent works have leveraged AI-assistance to improve instruction of tasks ranging from rehabilitation to surgical robot tele-operation. However, these works often make simplifying assumptions on the student learning process, and fail to model how a teacher's assistance interacts with different individuals' abilities when determining optimal teaching strategies. Inspired by the idea of scaffolding from educational psychology, we leverage shared autonomy, a framework for combining user inputs with robot autonomy, to aid with curriculum design. Our key insight is that the way a student's behavior improves in the presence of assistance from an autonomous agent can highlight which sub-skills might be most ``learnable'' for the student, or within their Zone of Proximal Development. We use this to design Z-COACH, a method for using shared autonomy to provide personalized instruction targeting interpretable task sub-skills. In a user study (n=50), where we teach high performance racing in a simulated environment of the Thunderhill Raceway Park with the CARLA Autonomous Driving simulator, we show that Z-COACH helps identify which skills each student should first practice, leading to an overall improvement in driving time, behavior, and smoothness. Our work shows that increasingly available semi-autonomous capabilities (e.g. in vehicles, robots) can not only assist human users, but also help *teach* them.

Problem

• Personalized instruction for motor skill learning
• AI-assisted teaching strategies interaction
• Shared autonomy for curriculum design

Innovation

• Leverages shared autonomy for teaching.
• Uses AI to personalize skill instruction.
• Identifies learnable sub-skills for students.