RobotKeyframing: Learning Locomotion with High-Level Objectives via Mixture of Dense and Sparse Rewards
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916466681446400 |
|---|---|
| author | Zargarbashi, Fatemeh Cheng, Jin Kang, Dongho Sumner, Robert Coros, Stelian |
| author_facet | Zargarbashi, Fatemeh Cheng, Jin Kang, Dongho Sumner, Robert Coros, Stelian |
| contents | This paper presents a novel learning-based control framework that uses keyframing to incorporate high-level objectives in natural locomotion for legged robots. These high-level objectives are specified as a variable number of partial or complete pose targets that are spaced arbitrarily in time. Our proposed framework utilizes a multi-critic reinforcement learning algorithm to effectively handle the mixture of dense and sparse rewards. Additionally, it employs a transformer-based encoder to accommodate a variable number of input targets, each associated with specific time-to-arrivals. Throughout simulation and hardware experiments, we demonstrate that our framework can effectively satisfy the target keyframe sequence at the required times. In the experiments, the multi-critic method significantly reduces the effort of hyperparameter tuning compared to the standard single-critic alternative. Moreover, the proposed transformer-based architecture enables robots to anticipate future goals, which results in quantitative improvements in their ability to reach their targets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_11562 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RobotKeyframing: Learning Locomotion with High-Level Objectives via Mixture of Dense and Sparse Rewards Zargarbashi, Fatemeh Cheng, Jin Kang, Dongho Sumner, Robert Coros, Stelian Robotics Artificial Intelligence Machine Learning This paper presents a novel learning-based control framework that uses keyframing to incorporate high-level objectives in natural locomotion for legged robots. These high-level objectives are specified as a variable number of partial or complete pose targets that are spaced arbitrarily in time. Our proposed framework utilizes a multi-critic reinforcement learning algorithm to effectively handle the mixture of dense and sparse rewards. Additionally, it employs a transformer-based encoder to accommodate a variable number of input targets, each associated with specific time-to-arrivals. Throughout simulation and hardware experiments, we demonstrate that our framework can effectively satisfy the target keyframe sequence at the required times. In the experiments, the multi-critic method significantly reduces the effort of hyperparameter tuning compared to the standard single-critic alternative. Moreover, the proposed transformer-based architecture enables robots to anticipate future goals, which results in quantitative improvements in their ability to reach their targets. |
| title | RobotKeyframing: Learning Locomotion with High-Level Objectives via Mixture of Dense and Sparse Rewards |
| topic | Robotics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2407.11562 |