Integrating learning and task planning for robots with Keras, including simulation, real robot, and multiple dataset support.

[NeurIPS 2023] We use large language models as commonsense world model and heuristic policy within Monte-Carlo Tree Search, enabling better-reasoned decision-making for daily task planning problems.

The hierarchical planner CHIMP (Conflict-driven Hierarchical Meta-CSP Planner).

[NeurIPS 2024] Official implementation for paper "Can Graph Learning Improve Planning in LLM-based Agents?"

Human Demo Videos to Robot Action Plans

Task Allocation Strategy to distribute goals in a fleet considering, goals makespan, goals position, robot capabilities and redundancy in the sensory system.

Planning domains motivated by real-world problems, particularly robotics applications, which contain incomplete knowledge, temporal and numeric requirements.

Task Allocation Strategy to distribute goals (in a decentralised manner) in a heterogeneous fleet considering, goals makespan, goals position, robot capabilities.

Tools to use ROSPlan in Python

A programmatic LLM prompt structure that enables plan generation functional across situated environments, robot capabilities, and tasks.

[CoRL 2022] BusyBot: Learning to Interact, Reason, and Plan in a BusyBoard Environment

Code for Transformers are Adaptable Task Planners, CoRL 2022

AI Task planners for decision making in ROSPlan

Teriyaki: A Framework to Generate Neurosymbolic PDDL-compliant Planners

Code for the paper "Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos" [NeurIPS (spotlight), 2024]

Code for the ICRA 2024 Cook2LTL paper on translating free-form cooking recipes to Linear Temporal Logic (LTL) formulae for robot task planning.

Turn STL formulas into maps and planed paths, control robots with DRL controllers.

Planning as In-Painting: A Diffusion-Based Embodied Task Planning Framework for Environments under Uncertainty

This is legacy code for the FOON API, which was originally written in Java. We highly recommend using the newer version written in Python.

Closed-Loop Long-Horizon Robotic Planning via Equilibrium Sequence Modeling