Diffusion-SAFE: Diffusion-Native Human-to-Robot Driving Handover for Shared Autonomy

TL;DR

Diffusion-SAFE introduces a diffusion-based framework for safe and smooth human-to-robot control handovers in shared autonomy, utilizing probabilistic risk detection and safety-guided plan steering.

Contribution

It presents a novel diffusion model approach for risk detection and control transfer, enabling continuous and safe handovers without hand-crafted score functions.

Findings

Achieves over 93% success rate in simulation

Achieves over 87% success rate on real robot

Ensures smooth control transitions during handovers

Abstract

Shared autonomy in driving requires anticipating human behavior, flagging risk before it becomes unavoidable, and transferring control safely and smoothly. We propose Diffusion-SAFE, a closed-loop framework built on two diffusion models: an evaluator that predicts multimodal human-intent action sequences for probabilistic risk detection, and a safety-guided copilot that steers its denoising process toward safe regions using the gradient of a map-based safety certificate. When risk is detected, control is transferred through partial diffusion: the human plan is forward-noised to an intermediate level and denoised by the safety-guided copilot. The forward-diffusion ratio $\rho$ acts as a continuous takeover knob-small $\rho$ keeps the output close to human intent, while increasing $\rho$ shifts authority toward the copilot, avoiding the mixed-unsafe pitfall of action-level blending. Unlike methods relying on hand-crafted score functions, our diffusion formulation supports both safety evaluation and plan generation directly from demonstrations. We evaluate Diffusion-SAFE in simulation and on a real ROS-based race car, achieving 93.0%/87.0% (sim/real) handover success rates with smooth transitions.