caelan/LTAMP
Learning for Task and Motion Planning (LTAMP)
This project helps roboticists and researchers design and execute multi-step manipulation plans for PR2 robots. It takes high-level task descriptions (like "pour coffee" or "stack blocks") and combines pre-defined and learned robotic actions to generate a sequence of movements. The output is a detailed motion plan that can be simulated and, potentially, executed on a physical PR2 robot.
No commits in the last 6 months.
Use this if you are developing or experimenting with complex robotic manipulation tasks for a PR2 robot and need to integrate both learned and pre-programmed actions.
Not ideal if you are working with non-PR2 robots, require only simple, single-step movements, or are looking for a commercial out-of-the-box solution.
Stars
60
Forks
7
Language
C++
License
GPL-3.0
Category
Last pushed
May 04, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/caelan/LTAMP"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
caelan/pddlstream
PDDLStream: Integrating Symbolic Planners and Blackbox Samplers
realkushagrakhare/3D_Path_Planning
AI project for 3D Path Planning. Other details and running instructions can be found on the...
DillonZChen/wlplan
Relational Features for Planning
enlite-ai/maze
Maze Applied Reinforcement Learning Framework
APLA-Toolbox/PythonPDDL
🧭🔍 A PDDL Planner in Python partially wrapping PDDL.jl using JuliaPy