English | Español
"Bridging the gap between probabilistic perception and deterministic execution."
This repository documents structured technical explorations in probabilistic robotics, control systems, and high-reliability embedded architectures.
The objective is to capture the structured reasoning required to build autonomous systems that operate in high-stakes, real-world environments—moving from uncertain measurements toward architectural certainty.
- Optimal State Estimation: Inferring reality from noisy and partial observations via recursive Bayesian filtering.
- Deterministic Autonomy: Addressing real-time constraints and hardware-software co-design for mission-critical reliability.
- Probabilistic Mapping: Spatial representation through Shannon entropy reduction and occupancy grid modeling.
- Control Theory: Stability, feedback mechanisms, and error correction in dynamic physical systems.
Below is the organized index of conceptual explorations and engineering intuitions:
- State Estimation: Inferring Reality from Noise
- The Kalman Filter: Optimal Linear Estimation
- Probabilistic Robotics: Managing Uncertainty
- Occupancy Grid Mapping: The Unknown Space
- Why Determinism is the Foundation of Autonomy
- PID Control: Feedback and Stability
- State Machine Design: Predictable Behavior
This logbook documents my technical maturity and engineering philosophy. It reflects a commitment to precision, documenting the transition from theoretical algorithms to deployable, autonomous robotic systems.
Emphasis is placed on system reliability under uncertainty, including noisy sensing, constrained computation, and asynchronous communication across distributed components.
MIT License | 2026
For deeper dives into specific limitations and failure modes:
→ https://github.com/Jorge-de-la-Flor/robotics-research-notes