A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approaches

Abstract

Task and Motion Planning (TAMP) integrates high-level task planning and low-level motion planning to equip robots with the autonomy to effectively reason over long-horizon, dynamic tasks. Optimization-based TAMP focuses on hybrid optimization approaches that define goal conditions via objective functions and are capable of handling open-ended goals, robotic dynamics, and physical interaction between the robot and the environment. Therefore, optimization-based TAMP is particularly suited to solve highly complex, contact-rich locomotion and manipulation problems. This survey provides a comprehensive review on optimization-based TAMP, covering (i) planning domain representations, including action description languages and temporal logic, (ii) individual solution strategies for components of TAMP, including AI planning and trajectory optimization (TO), and (iii) the dynamic interplay between logic-based task planning and model-based TO. A particular focus of this survey is to highlight the algorithm structures to efficiently solve TAMP, especially hierarchical and distributed approaches. Additionally, the survey emphasizes the synergy between the classical methods and contemporary learning-based innovations such as large language models. Furthermore, the future research directions for TAMP is discussed in this survey, highlighting both algorithmic and application-specific challenges.

26 pages, 13 figures, published at IEEE/ASME Transactions on Mechatronics

References in corpus (25)

• PDDL2.1: An Extension to PDDL for Expressing Temporal Planning Domains
• Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
• The Fast Downward Planning System
• Modelling Mixed Discrete-Continuous Domains for Planning
• Text2Motion: From Natural Language Instructions to Feasible Plans
• Learning Symbolic Models of Stochastic Domains
• Robust Temporal Logic Model Predictive Control
• Simultaneous Contact, Gait and Motion Planning for Robust Multi-Legged Locomotion via Mixed-Integer Convex Optimization
• Asymptotically Optimal Sampling-Based Motion Planning Methods
• Structured contact force optimization for kino-dynamic motion generation
• Versatile Multi-Contact Planning and Control for Legged Loco-Manipulation
• Object-Centric Task and Motion Planning in Dynamic Environments
• Evaluating direct transcription and nonlinear optimization methods for robot motion planning
• Integrating Action Knowledge and LLMs for Task Planning and Situation Handling in Open Worlds
• Model Hierarchy Predictive Control of Robotic Systems
• Neural Manipulation Planning on Constraint Manifolds
• Receding Horizon Task and Motion Planning in Changing Environments
• Robust Task and Motion Planning for Long-Horizon Architectural Construction Planning
• Optimal task and motion planning and execution for human-robot multi-agent systems in dynamic environments
• Simultaneous Contact-Rich Grasping and Locomotion via Distributed Optimization Enabling Free-Climbing for Multi-Limbed Robots
• Robust Multi-Robot Trajectory Optimization Using Alternating Direction Method of Multiplier
• Accelerating Model Predictive Control for Legged Robots through Distributed Optimization
• Logic programming for deliberative robotic task planning
• Active Learning of Abstract Plan Feasibility
• Fast MILP-based Task and Motion Planning for Pick-and-Place with Hard/Soft Constraints of Collision-Free Route

Cited by in corpus (4)

• Large Language Models for Combinatorial Optimization: A Systematic Review
• LLM-GROP: Visually Grounded Robot Task and Motion Planning with Large Language Models
• SIT-LMPC: Safe Information-Theoretic Learning Model Predictive Control for Iterative Tasks
• Cross-Entropy Optimization of Physically Grounded Task and Motion Plans