Technology Category
Intelligent Robots: Human-Robot InteractionHumans and AI: Human-Aware Planning and Behavior PredictionComputer Vision: Vision for Robotics & Autonomous Driving
Vision-Based Human Awareness Estimation for Enhanced Safety and Efficiency of AMRs in Industrial Warehouses
🤖 AI Summary
This work addresses the limitation of existing autonomous mobile robots (AMRs) that treat humans as generic dynamic obstacles, leading to overly conservative motion and an inability to optimize interaction based on whether humans are aware of the robot. For the first time, the proposed approach integrates human perceptual states into the AMR decision-making framework by leveraging a monocular RGB camera to estimate 3D human pose and head orientation in real time. A viewing frustum model is then employed to infer human attention status, enabling dynamic adaptation of the robot’s navigation strategy. The method is validated using synthetic data in NVIDIA Isaac Sim and demonstrates efficient and accurate attention-aware navigation in real-world warehouse environments. By moving beyond conventional collision-avoidance paradigms, this study significantly enhances both operational efficiency and safety in human–robot coexistence scenarios.
Technology Category
Application Category
📝 Abstract
Ensuring human safety is of paramount importance in warehouse environments that feature mixed traffic of human workers and autonomous mobile robots (AMRs). Current approaches often treat humans as generic dynamic obstacles, leading to conservative AMR behaviors like slowing down or detouring, even when workers are fully aware and capable of safely sharing space. This paper presents a real-time vision-based method to estimate human awareness of an AMR using a single RGB camera. We integrate state-of-the-art 3D human pose lifting with head orientation estimation to ascertain a human's position relative to the AMR and their viewing cone, thereby determining if the human is aware of the AMR. The entire pipeline is validated using synthetically generated data within NVIDIA Isaac Sim, a robust physics-accurate robotics simulation environment. Experimental results confirm that our system reliably detects human positions and their attention in real time, enabling AMRs to safely adapt their motion based on human awareness. This enhancement is crucial for improving both safety and operational efficiency in industrial and factory automation settings.
Problem
Research questions and friction points this paper is trying to address.
human awareness
autonomous mobile robots
industrial warehouses
safety
human-robot interaction
Innovation
Methods, ideas, or system contributions that make the work stand out.
human awareness estimation
vision-based perception
3D human pose lifting
head orientation estimation
autonomous mobile robots
🔎 Similar Papers
No similar papers found.
