Integrated task and motion planning

CR Garrett, R Chitnis, R Holladay, B Kim… - Annual review of …, 2021‏ - annualreviews.org
The problem of planning for a robot that operates in environments containing a large
number of objects, taking actions to move itself through the world as well as to change the …

A survey on deep learning and deep reinforcement learning in robotics with a tutorial on deep reinforcement learning

EF Morales, R Murrieta-Cid, I Becerra… - Intelligent Service …, 2021‏ - Springer
This article is about deep learning (DL) and deep reinforcement learning (DRL) works
applied to robotics. Both tools have been shown to be successful in delivering data-driven …

Voxposer: Composable 3d value maps for robotic manipulation with language models

W Huang, C Wang, R Zhang, Y Li, J Wu… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Large language models (LLMs) are shown to possess a wealth of actionable knowledge that
can be extracted for robot manipulation in the form of reasoning and planning. Despite the …

Text2motion: From natural language instructions to feasible plans

K Lin, C Agia, T Migimatsu, M Pavone, J Bohg - Autonomous Robots, 2023‏ - Springer
Abstract We propose Text2Motion, a language-based planning framework enabling robots
to solve sequential manipulation tasks that require long-horizon reasoning. Given a natural …

Rekep: Spatio-temporal reasoning of relational keypoint constraints for robotic manipulation

W Huang, C Wang, Y Li, R Zhang, L Fei-Fei - arxiv preprint arxiv …, 2024‏ - arxiv.org
Representing robotic manipulation tasks as constraints that associate the robot and the
environment is a promising way to encode desired robot behaviors. However, it remains …

Grounded decoding: Guiding text generation with grounded models for robot control

W Huang, F **a, D Shah, D Driess, A Zeng, Y Lu… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Recent progress in large language models (LLMs) has demonstrated the ability to learn and
leverage Internet-scale knowledge through pre-training with autoregressive models …

Deep affordance foresight: Planning through what can be done in the future

D Xu, A Mandlekar, R Martín-Martín… - … on robotics and …, 2021‏ - ieeexplore.ieee.org
Planning in realistic environments requires searching in large planning spaces. Affordances
are a powerful concept to simplify this search, because they model what actions can be …

Grounded decoding: Guiding text generation with grounded models for embodied agents

W Huang, F **a, D Shah, D Driess… - Advances in …, 2024‏ - proceedings.neurips.cc
Recent progress in large language models (LLMs) has demonstrated the ability to learn and
leverage Internet-scale knowledge through pre-training with autoregressive models …

Deep visual reasoning: Learning to predict action sequences for task and motion planning from an initial scene image

D Driess, JS Ha, M Toussaint - arxiv preprint arxiv:2006.05398, 2020‏ - arxiv.org
In this paper, we propose a deep convolutional recurrent neural network that predicts action
sequences for task and motion planning (TAMP) from an initial scene image. Typical TAMP …

Learning to solve sequential physical reasoning problems from a scene image

D Driess, JS Ha, M Toussaint - The International Journal of …, 2021‏ - journals.sagepub.com
In this article, we propose deep visual reasoning, which is a convolutional recurrent neural
network that predicts discrete action sequences from an initial scene image for sequential …