What I personally accomplished this week on the project: I focused on validating our architecture and proposal numbers with real interfaces and a clean internal pipeline. I mapped all hardware interfaces (USB camera to Raspberry Pi, ultrasonic TRIG/ECHO to GPIO, PWM + direction to motor driver, and power to the base) and corrected the Raspberry Pi internal flow to be strictly downstream (capture → preprocessing → YOLOv8 → detections → tracking → distance/bearing → controller → safety gate → motor commands). The following is our design’s architecture with modules and interfaces.
I also analyzed whether our quantitative targets (≥15 FPS, ≤200 ms stop under 30 cm, ≤1 m/s speed, and 1.25 m ± 0.25 m following distance) are technically plausible given compute latency and signal paths. In addition, I studied YOLOv8’s architecture and why it is suitable for real-time indoor person detection, and I learned how to implement and structure its inference loop on Raspberry Pi.
Is my progress on schedule or behind: I am on schedule for my assigned vision and benchmarking tasks. This week reduced architectural risk by grounding our design in concrete interfaces and confirming that our stated requirements align with subsystem responsibilities. I now have concrete artifacts (architecture diagram with interfaces and YOLOv8 architecture reference) ready to include as evidence in the status report and website.
What deliverables do I hope to complete in the next week: I will finalize a clean architecture diagram with correct signal flow and a single safety override merge point, implement a minimal YOLOv8 vision loop on Raspberry Pi and log sustained FPS to validate the ≥15 FPS target, and integrate a lightweight tracking layer so the output becomes a stable target state for the controller.