Distributed wireless sensing detects hidden objects for safer robots
Leveraging Distributed Sensing and Hyperdimensional Computing for Non-Line-of-Sight Passive Object Sensing
RoboticsEmerging Technologies
Summary
In factories where robots work alongside humans, it’s important to spot people or obstacles even when they’re out of sight. The authors present a way to use wireless signals, already present in the environment, to detect hidden objects without needing cameras or sensors pointing directly at them. They turn these signals into high-dimensional data patterns that help the system learn and recognize unseen hazards. Tests in simulated factory settings show this method can detect hidden objects accurately and help robots avoid potential collisions.
What this means in practice
- •For industrial automation teams: Improve robot safety by detecting hidden humans and obstacles using existing wireless signals in factory environments.
- •For warehouse operations managers: Enhance autonomous vehicle path planning with better awareness of unseen risks caused by occlusions or obstacles.
Authors
Placido Mursia, Marco Rossanese, Francesco Devoti, Adrian Lendinez Ibanez, Lanfranco Zanzi, Xi Li, Xavier Costa-Perez
Abstract
In smart factory environments, passive entities such as humans and movable obstacles may interfere with autonomous robot operations, posing significant safety risks. Detecting potential conflicts between robots and entities outside their field-of-view (FoV) is therefore of paramount importance. However, conventional passive object detection systems rely on sensors such as LiDAR, radar, or cameras, which operate under direct line-of-sight (LoS) and are limited by obstacles and occlusions. To overcome these limitations, integrated sensing and communication (ISAC) enables environmental perception via the communication infrastructure thanks to cooperation among distributed wireless devices. In this paper, we propose a framework for passive entity sensing beyond the robot's FoV that relies solely on distributed channel measurements from the communication infrastructure to perform risk-aware classification. These measurements are embedded into high-dimensional representations using hyperdimensional computing (HDC), enabling robust and scalable learning without explicit channel reconstruction. Numerical simulations based on a commercial ray tracer and ROS-based validation in realistic smart factory scenarios demonstrate improved safety and enhanced path planning with up to 89% accuracy under severe occlusions, while maintaining low computational complexity.