Combined task and motion planning through an extensible planner-independent interface layer

By Siddharth Srivastava, Eugene Fang, Lorenzo Riano, Rohan Chitnis, Stuart J. Russell, Pieter Abbeel. 2014

550 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Control and Systems Engineering, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

In Robotics & Control

Citations in the corpus

Do As I Can, Not As I Say: Grounding Language in Robotic Affordances (2022, background): “Task and motion planning [59, 60] is a problem of sequencing tasks to solve a high-level problem, while ensuring the feasibility given an embodiment (task”
Inner Monologue: Embodied Reasoning through Planning with Language Models (2022, background): “Task and motion planning [22, 23] requires simultaneously solving a high-level, discrete task planning problem [24, 25, 26], and a low-level, continuous motion planning problem [27].”
Overcoming Exploration in Reinforcement Learning with Demonstrations (2017, background): “More recent work on task and motion planning considers both logical and physical aspects of the task [27], [28], [29], but requires domainspecific engineering.”
IQA: Visual Question Answering in Interactive Environments (2017, background): “A large body of research on planning algorithms [12, 14, 26, 62, 63] use high-level formal languages.”
Visual Semantic Planning Using Deep Successor Representations (2017, background): “Task-level planning [10, 13, 20, 47, 48] addresses the problem of finding a high-level plan for performing a task.”
ManipulaTHOR: A Framework for Visual Object Manipulation (2021, background): “Past works for visual object manipulation tend to use modular designs to solve this problem [25, 30, 14] – for instance, employing object detection models, instance segmentation models, point cloud estimators, etc. and then feeding these outputs into a planner.”
Visual Room Rearrangement (2021, background): “Our work can be considered as an instance of joint task and motion planning [25, 43, 35, 17, 12] since solving the rearrangement task requires low-level motion planning to plan a sequence of actions and high-level task planning to recover the goal state from the initial state of the scene.”
Deep Visual Reasoning: Learning to Predict Action Sequences for Task and Motion Planning from an Initial Scene Image (2020, methodology): “A general approach to TAMP is to combine discrete logic search with a sampling-based motion planning algorithm [24, 7, 40, 6] or constraint satisfaction methods [27, 28, 31].”
Discovering State and Action Abstractions for Generalized Task and Motion Planning (2021, background): “This task is known to be difficult for TAMP solvers and has previously required significant engineering, including collision error feedback, to be feasible in large problems (Srivastava et al. 2014).”
Integrated Task and Motion Planning (2020, methodology): “Several tamp approaches have proposed heuristic methods for diagnosing failure and repairing the problem (74, 75, 76, 60).”
Neural Task Graphs: Generalizing to Unseen Tasks From a Single Video Demonstration (2018, background): “Conventionally task planning focuses on high-level plans and low-level state spaces [10, 36].”
Logic-Geometric Programming: An Optimization-Based Approach to Combined Task and Motion Planning (2015, methodology): “Garrett et al. [2014] addresses the problem in a way that uses symbols (CanGrasp and Reachable) to represent geometric preconditions for actions also on the symbolic level.”
Hierarchical Expertise-Level Modeling for User Specific Robot-Behavior Explanations (2018, methodology): “Starting out we can convert each of the continuous arguments into geometric symbols (this is similar to the approach used in [ Srivastava et al., 2014 ] ).”
Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs (2020, methodology): “Our approach to factorizing long-term manipulation planning into the task level and the motion level has a strong resemblance to task-and-motion planning (TAMP) methods [5, 16, 23, 30].”
Physically Embedded Planning Problems: New Challenges for Reinforcement Learning (2020, methodology): “, 2018), and progress in this area has largely been driven by the design and engineering of domain-specific hand-crafted and structured methods (Dantam et al., 2016; Kaelbling and Lozano-Pérez, 2011; Plaku and Hager, 2010; Siméon et al., 2004; Srivastava et al., 2014; Toussaint, 2015), which typical”
Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation (2019, methodology): “Similarly, completing long horizon tasks has also been explored with symbolic models (Toussaint et al., 2019) and Task and Motion Planning (TAMP) (Kaelbling & Lozano-Perez, 2011; Srivastava et al., 2014).”
PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planning (2018, background): “…approaches to robotic task and motion planning have developed strategies for handling continuous spaces that go beyond prediscretization (Kaelbling and LozanoPérez 2011; Srivastava et al. 2014; Garrett, Lozano-Pérez, and Kaelbling 2015; Toussaint 2015; Garrett, Lozano-Pérez, and Kaelbling 2017).”