Sense–Plan–Code–Act (SPCA) framework — LLM+PDDL planning, code generation and ROS2/UR5 simulation for embodied robotic manipulation.
-
Updated
Apr 13, 2026 - Jupyter Notebook
Sense–Plan–Code–Act (SPCA) framework — LLM+PDDL planning, code generation and ROS2/UR5 simulation for embodied robotic manipulation.
Official repository for my MSc thesis: "Addressing Goal Misgeneralization with Natural Language Interfaces."
Code for the Paper: Data Augmentation for Instruction Following Policies via Trajectory Segmentation (https://arxiv.org/abs/2503.01871)
Reinforcement learning on LLMs in multi-step text-based environments.
Add a description, image, and links to the babyai topic page so that developers can more easily learn about it.
To associate your repository with the babyai topic, visit your repo's landing page and select "manage topics."