Two research papers explore methods for improving visual affordance segmentation on embedded devices, particularly for wearable robots. The first paper focuses on enhancing the decoder module of lightweight neural networks to balance generalization performance with computational cost. The second paper introduces approaches using RGB-D cameras and hardware-aware neural architecture search to achieve Pareto optimality between performance and hardware constraints, demonstrating real-time capabilities within a battery-compatible energy budget. AI
IMPACT These papers advance techniques for efficient AI model deployment on resource-constrained devices, crucial for real-time applications in robotics and embedded systems.
RANK_REASON Two academic papers published on arXiv detailing novel methods for computer vision tasks.
- Jetson Nano
- RealSense, Inc.
- RGB-D Visual Simultaneous Localization and Mapping (SLAM) Application
- arXiv
- Deep Neural Networks
- Filling the Pareto-Optimal Front for Affordance Segmentation on Embedded Devices Using RGB-D Cameras
- Lightweight Neural Networks for Affordance Segmentation: Enhancement of the Decoder Module
- RGB-D Cameras
- Wearable Robots: An Original Mechatronic Design of a Hand Exoskeleton for Assistive and Rehabilitative Purposes
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
