Multi-contact loco-manipulation trajectories for the ANYmal robot with a 6-DoF Arm

Loco-manipulation planning skills are pivotal for expanding the utility of robots in everyday environments. These skills can be assessed based on a system's ability to coordinate complex holistic movements and multiple contact interactions when solving different tasks. However, existing approaches have been merely able to shape such behaviors with hand-crafted state machines, densely engineered rewards, or pre-recorded expert demonstrations. Here, we propose a minimally-guided framework that automatically discovers whole-body trajectories jointly with contact schedules for solving general loco-manipulation tasks in pre-modeled environments. The key insight is that multi-modal problems of this nature can be modeled within the context of integrated Task and Motion Planning (TAMP), resulting in a tractable bilevel optimization formulation. An effective bilevel search strategy is achieved owing to the fusion of domain-specific rules with the well-established strengths of different planning ..., This dataset was generated using the algorithm described in the article titled \"Versatile Multi-Contact Planning and Control for General Loco-Manipulation\".,

移动操作规划技能（Loco-manipulation planning skills）对于拓展机器人在日常环境中的应用价值至关重要。此类技能可通过系统在解决不同任务时协调复杂整体运动与多接触交互的能力进行评估。然而，现有方法仅能通过手工设计的状态机、精心调校的奖励函数，或预先录制的专家演示来塑造此类行为。本文提出一种低引导度框架，可自动发现全身运动轨迹与接触规划方案，以解决预建模环境中的通用移动操作任务。核心见解在于，此类多模态问题可在集成任务与运动规划（Task and Motion Planning, TAMP）的框架下建模，从而得到易处理的双层优化公式。通过将特定领域规则与各类规划方法的成熟优势相融合，我们实现了高效的双层搜索策略。本数据集基于发表于《面向通用移动操作的多接触规划与控制》（Versatile Multi-Contact Planning and Control for General Loco-Manipulation）一文的算法生成。