behavior-trees

UCSC - CMPM 146 - Game AI - Python

Behaviour trees in Python made easy!

A Behavior Tree library in Python

MSc thesis: LLM-generated behaviour trees for robot task planning — natural-language commands to pick-and-place control of an ABB IRB 4600 in CoppeliaSim.

Very basic behavior tree framework for Python

autonomous mobile robot system for item retrieval within a simulated environment | demonstrates an integrated approach to autonomous exploration, obstacle avoidance, item detection, retrieval, and efficient navigation back to a home zone

ROS 2 bringup package for the Caltech M4 morphobot — launch files, configs and behavior trees

a React-inspired incremental behaviour tree library

REactive Behavior Constraint-Aware Tree learning (REBCAT) - a human-robot collaboration framework to learn task from demonstrations. Interpretable, fast, object-centric, and reactive.

A skill-based platform for ROS v.2 with knowledge representating, planning and reasoning

🤖 Advanced multi-agent robotics system using ROS2, NVIDIA Isaac Sim, behavior trees, and RL locomotion controllers. Features mobile manipulator, forklift, and Spot robot with autonomous navigation and manipulation. Graduation Project 2025.

AI gameplay patterns for Godot: LLM-driven NPCs, behavior trees, Python bridge, local Ollama

A package for Grammatical Evolution and other Agent-Base Modeling (ABM) experiments.

A Python library offering a Behavior Tree implementation which focuses on contingency handling - the key to master complex applications which operate in dynamic worlds.

Behavior trees, computational geometry & multi-agent motion planning — Dubins/Reeds-Shepp curves, RRT*, deadlock-aware coordination

Autonomous palletizing cell in ROS 2 Jazzy + Gazebo Harmonic: UR10e, RGB-D measurement of unknown cartons and pallets, interlocked layer patterns, MoveIt 2 pick & place, BehaviorTree.CPP

The specification, reference runtimes, validator, LLM bridge, and conformance suite for URML — an open language for robot intent.

Full-stack ROS 2 autonomous navigation: Nav2, SLAM Toolbox, RTAB-Map & ORB-SLAM3 VSLAM, Gazebo Harmonic, Docker, multi-robot fleet coordination, collaborative loop closure, coordinated frontier exploration, MPPI controller, behavior trees, waypoint following & Gaussian Splatting capture on Humble/Jazzy.

Autonomous warehouse delivery rover in ROS 2 Humble: Nav2/MPPI navigation, YOLO perception, and a py_trees behaviour tree that recovers when the cargo isn't there.

Three-layer deterministic safety & ethical execution guard for autonomous robots (ROS 2 & Behavior Trees). Sub-ms physical reflex (QERRA-HSR) + moral filter (SEMEV-12) + values ranker (THRIVE). Fully auditable.