AI, Embedded System and Robotics
summary
RDKX5 runs YOLO v8n quantized to int8 on a Raspberry‑Pi‑like board and claims up to 220 FPS for object detection and faster instance segmentation with minimal accuracy loss; a humanoid demo links offline KWS/ASR and on‑cloud LLM memorization to call control APIs for pose and gesture responses; reinforcement learning tunes motion for robotic dogs; a model zoo plus Python/C++ samples and documented flashing workflow let teams reproduce the deployments.
AI-written summary · about
chapters (7)
- 0:00AI embedded systems intro
- 1:49AI in computer vision
- 3:59YOLOv8 on embedded
- 8:47RDK for AI models
- 12:25Voice interaction demos
- 16:24D Robotics ecosystem
- 20:23Developer support
related talks
01h 02mAI on the Edge
37mUnstructured Data Processing with a Raspberry Pi AI Kit and Python
28mChasing birds with code
15mDeterministic, Adaptive, and Sustainable Robotics
44mAdventures in Puppy Training with A.I. and a Raspberry Pi
43mBuilding Qrio, a Bot That Plays Videos for My Toddler
04mRandom Interviews 3
20mScaling Edge AI with Elixir and Nerves