Assistive Navigation Using Deep Reinforcement Learning Guiding Robot With UWB/Voice Beacons and Semantic Feedbacks for Blind and Visually Impaired People
Problem
People who are blind and visually impaired struggle to navigate pedestrian environments independently, and SLAM-based robots are vulnerable in dynamic settings.
Why it matters
Independent mobility is described as critical for blind and visually impaired people.
What the AI did
A deep reinforcement learning-based guiding robot with UWB/voice beacons was designed to navigate designated waypoints, avoid obstacles, and give intuitive audio feedback to users via a handle device.
Results
not stated in source
Impact
The abstract claims the robot can effectively avoid obstacles and suit dynamic pedestrian environments, but no measured results are given.
Record
| Venue | Frontiers in Robotics and AI |
|---|---|
| Published | 2021 |
| Work type | article |
| Authors | Chen-Lung Lu, Ziyan Liu, Jui-Te Huang, Ching-I Huang, Bo-Hui Wang, Yi Chen, Nien-Hsin Wu, Hsueh‐Cheng Wang et al. |
| Citations | 48 (OpenAlex, at import time) |
| References | 53 |
| Model or method | Deep reinforcement learning (DRL) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3389/frobt.2021.654132 |
| Open access | gold |
| Keywords | deep reinforcement learning, assistive robot, UWB beacons, visually impaired, navigation, obstacle avoidance |
Importance rating
significant — thousands to millions affected
Independent mobility for blind and visually impaired people is called critical; a genuinely new assistive capability, but no scale stated and no measured results reported.
More in Robotics & Autonomy
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Autonomous robotic laparoscopic surgery for intestinal anastomosis | 2022 | 384 |
7
|
| 2 | Solving Rubik's Cube with a Robot Hand | 2019 | 569 |
6
|
| 3 | PaLM-E: An Embodied Multimodal Language Model | 2023 | 346 |
6
|
| 4 | Towards Deep Radar Perception for Autonomous Driving: Datasets, Methods, and Challenges | 2022 | 154 |
6
|
| 5 | Learning robust autonomous navigation and locomotion for wheeled-legged robots | 2024 | 132 |
6
|