DynNav is a 26-contribution research framework for uncertainty-aware, risk-sensitive autonomous navigation in unknown environments — built on ROS 2 Humble, validated on TurtleBot3, spanning belief-space planning, formal safety shields, and Byzantine-fault-tolerant swarm consensus.
Most navigation stacks assume the map, the sensors, and other agents behave well. Real deployments — disaster response, warehouse fleets, planetary rovers, assistive robots — break that assumption constantly. DynNav treats the failure modes of autonomy as first-class research problems rather than edge cases, decomposing navigation under uncertainty into 26 independent, testable contributions: each pairs a focused research question with implementation, experiments, and reproducible results, integrated into a common ROS 2 stack.
Four layers sit above a ROS 2 / Gazebo / TurtleBot3 foundation. Foundation models and the learning layer feed structured planning; the safety layer filters every command before it reaches the robot.
LiDAR / odometry stream into EKF–UKF belief-state estimation.
Belief-space occupancy is converted into a CVaR-weighted risk map.
Risk-weighted A* / D* searches over the belief-space cost field.
STL monitors and CBF filters check the candidate command against safety constraints.
Safe-mode FSM triggers conservative behaviour or replanning if risk crosses threshold.
Each contribution is an independent module: a research question, an implementation, an experiment script, and a results folder. Filter by category, or browse all.
Figures reported below are drawn from each module's own experiment logs (contributions/*/results/*.csv). They reflect each module's standalone evaluation protocol, not a single unified benchmark.
| Metric | No shield | With shield |
|---|---|---|
| Constraint violations / episode | 4.2 avg | 0.3 avg |
| Path length overhead | — | < 8% |
| Avg. command correction | — | 0.026 m/s |
| Metric | Naive majority | BFT weighted median |
|---|---|---|
| Byzantine detection rate | 60% | 91% |
| Correct plan selected | 71% | 96% |
| Byzantine fault tolerance | f < N/2 | f < N/3 |
| Round | Centralised (MSE) | Federated (MSE) |
|---|---|---|
| 1 | 0.41 | 0.37 |
| 10 | 0.18 | 0.21 |
| 20 | 0.12 | 0.14 |
| Training | Episodes to "hard" stage | Final success rate |
|---|---|---|
| Flat (no curriculum) | N/A | 23% |
| Adaptive curriculum | ~200 | 61% |
Placeholders for simulation captures and demo recordings — replace with exported assets from data/plots/ and Gazebo screen recordings.
A full technical writeup is in TECHNICAL_REPORT.md in the repository. The questions below cover the project's scope honestly.
Not yet. It is 26 independent research modules sharing a common ROS 2 target and simulation environment. Several modules are integrated into the core planning/safety loop; others are standalone studies. See Future Work for the integration roadmap.
Each table is produced by that module's own evaluation script. A single command reproducing every table at once does not yet exist — this is the top item in Future Work.
TurtleBot3 Burger (physical) and TurtleBot3 Waffle in Gazebo, on ROS 2 Humble / Ubuntu 22.04, with WSL2 supported for development.
Yes — the repository is Apache-2.0 licensed. See the Citation section below for how to credit the work.
Electrical & Computer Engineering
Democritus University of Thrace
Research interests: uncertainty-aware planning, risk-sensitive control, formal safety for learning-enabled robotic systems, multi-robot coordination.
Open to research collaboration and graduate study opportunities in robotics & autonomous systems.
If you use DynNav in your research, please cite the software release.