EvoPlan: Evolutionary Neuro-Symbolic Robot Planning with Spatio-Temporal Guarantees
EvoPlan: Evolutionary Neuro-Symbolic Robot Planning with Spatio-Temporal Guarantees
This paper introduces EvoPlan, a neuro-symbolic framework that combines evolutionary search with Signal Temporal Logic constraints to ensure plan validity and safety for robot navigation and manipulation tasks. The system includes three components: an offline procedure that mines global mobility constraints from demonstrations, an evolutionary PDDL planner that iteratively repairs LLM-generated plans using programmatic validators, and a constrained execution loop that grounds plans in Nav2 costmaps and updates replanning upon constraint violations. Demonstrations include Bench2Drive, HA-VLN-CE, ALFWorld, NL-PDDL Blocksworld, Gazebo simulations, and physical tests on a Clearpath Jackal robot.
The authors present EvoPlan, a neuro-symbolic framework combining evolutionary search with Signal Temporal Logic constraints to ensure plan validity and safety for robot navigation and manipulation tasks.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- code: not_reported
- weights: not_reported
- dataset: not_reported
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
ne in Gazebo and on a Clearpath Jackal robot. More details and videos are on the project page: https://nbhavyasai.github.io/evoplan/
Open source S6
Source：arXiv Robotics — research abstracts · arxiv.org