Towards Quadrupedal Jumping and Walking for Dynamic Locomotion using Reinforcement Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914118890422272 |
|---|---|
| author | Olsen, Jørgen Anker Pettersen, Lars Rønhaug Alexis, Kostas |
| author_facet | Olsen, Jørgen Anker Pettersen, Lars Rønhaug Alexis, Kostas |
| contents | This paper presents a curriculum-based reinforcement learning framework for training precise and high-performance jumping policies for the robot `Olympus'. Separate policies are developed for vertical and horizontal jumps, leveraging a simple yet effective strategy. First, we densify the inherently sparse jumping reward using the laws of projectile motion. Next, a reference state initialization scheme is employed to accelerate the exploration of dynamic jumping behaviors without reliance on reference trajectories. We also present a walking policy that, when combined with the jumping policies, unlocks versatile and dynamic locomotion capabilities. Comprehensive testing validates walking on varied terrain surfaces and jumping performance that exceeds previous works, effectively crossing the Sim2Real gap. Experimental validation demonstrates horizontal jumps up to 1.25 m with centimeter accuracy and vertical jumps up to 1.0 m. Additionally, we show that with only minor modifications, the proposed method can be used to learn omnidirectional jumping. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_24584 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Quadrupedal Jumping and Walking for Dynamic Locomotion using Reinforcement Learning Olsen, Jørgen Anker Pettersen, Lars Rønhaug Alexis, Kostas Robotics This paper presents a curriculum-based reinforcement learning framework for training precise and high-performance jumping policies for the robot `Olympus'. Separate policies are developed for vertical and horizontal jumps, leveraging a simple yet effective strategy. First, we densify the inherently sparse jumping reward using the laws of projectile motion. Next, a reference state initialization scheme is employed to accelerate the exploration of dynamic jumping behaviors without reliance on reference trajectories. We also present a walking policy that, when combined with the jumping policies, unlocks versatile and dynamic locomotion capabilities. Comprehensive testing validates walking on varied terrain surfaces and jumping performance that exceeds previous works, effectively crossing the Sim2Real gap. Experimental validation demonstrates horizontal jumps up to 1.25 m with centimeter accuracy and vertical jumps up to 1.0 m. Additionally, we show that with only minor modifications, the proposed method can be used to learn omnidirectional jumping. |
| title | Towards Quadrupedal Jumping and Walking for Dynamic Locomotion using Reinforcement Learning |
| topic | Robotics |
| url | https://arxiv.org/abs/2510.24584 |