BT-TL-DMPs: A Novel Robot TAMP Framework Combining Behavior Tree, Temporal Logic and Dynamical Movement Primitives

2025-07-19

AI Summary

Robot learning from demonstration (LfD) struggles with generalizing long-horizon, multi-stage manipulation tasks—especially under dynamic changes in task goals, motion requirements, and complex spatiotemporal constraints. Method: This paper proposes a hierarchical framework integrating Behavior Trees (BTs), Signal Temporal Logic (STL), and Dynamic Movement Primitives (DMPs). STL is innovatively employed to formally specify task constraints and systematically translated into reactive BT structures. Furthermore, an STL-constraint-driven optimization of DMP forcing terms is introduced, ensuring strict satisfaction of spatiotemporal logical constraints while preserving demonstrated dynamical features. Results: Simulation and real-robot experiments demonstrate significantly improved cross-scenario skill transfer. The framework effectively bridges the semantic gap between high-level symbolic planning and low-level motion control, enhancing both reliability and adaptability in complex manipulation tasks.

Technology Category

• Intelligent Robots: Manipulation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

In the field of Learning from Demonstration (LfD), enabling robots to generalize learned manipulation skills to novel scenarios for long-horizon tasks remains challenging. Specifically, it is still difficult for robots to adapt the learned skills to new environments with different task and motion requirements, especially in long-horizon, multi-stage scenarios with intricate constraints. This paper proposes a novel hierarchical framework, called BT-TL-DMPs, that integrates Behavior Tree (BT), Temporal Logic (TL), and Dynamical Movement Primitives (DMPs) to address this problem. Within this framework, Signal Temporal Logic (STL) is employed to formally specify complex, long-horizon task requirements and constraints. These STL specifications are systematically transformed to generate reactive and modular BTs for high-level decision-making task structure. An STL-constrained DMP optimization method is proposed to optimize the DMP forcing term, allowing the learned motion primitives to adapt flexibly while satisfying intricate spatiotemporal requirements and, crucially, preserving the essential dynamics learned from demonstrations. The framework is validated through simulations demonstrating generalization capabilities under various STL constraints and real-world experiments on several long-horizon robotic manipulation tasks. The results demonstrate that the proposed framework effectively bridges the symbolic-motion gap, enabling more reliable and generalizable autonomous manipulation for complex robotic tasks.

Problem

• Generalize robot skills to new long-horizon tasks
• Adapt learned motions to complex spatiotemporal constraints
• Bridge symbolic and motion planning for reliable manipulation

Innovation

• Integrates BT, TL, DMPs for robot tasks
• Uses STL to specify task constraints
• Optimizes DMPs with STL constraints