VL-TGS: Trajectory Generation and Selection using Vision Language Models in Mapless Outdoor Environments
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913840127541248 |
|---|---|
| author | Song, Daeun Liang, Jing Xiao, Xuesu Manocha, Dinesh |
| author_facet | Song, Daeun Liang, Jing Xiao, Xuesu Manocha, Dinesh |
| contents | We present a multi-modal trajectory generation and selection algorithm for real-world mapless outdoor navigation in human-centered environments. Such environments contain rich features like crosswalks, grass, and curbs, which are easily interpretable by humans, but not by mobile robots. We aim to compute suitable trajectories that (1) satisfy the environment-specific traversability constraints and (2) generate human-like paths while navigating on crosswalks, sidewalks, etc. Our formulation uses a Conditional Variational Autoencoder (CVAE) generative model enhanced with traversability constraints to generate multiple candidate trajectories for global navigation. We develop a visual prompting approach and leverage the Visual Language Model's (VLM) zero-shot ability of semantic understanding and logical reasoning to choose the best trajectory given the contextual information about the task. We evaluate our method in various outdoor scenes with wheeled robots and compare the performance with other global navigation algorithms. In practice, we observe an average improvement of 20.81% in satisfying traversability constraints and 28.51% in terms of human-like navigation in four different outdoor navigation scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_02454 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | VL-TGS: Trajectory Generation and Selection using Vision Language Models in Mapless Outdoor Environments Song, Daeun Liang, Jing Xiao, Xuesu Manocha, Dinesh Robotics We present a multi-modal trajectory generation and selection algorithm for real-world mapless outdoor navigation in human-centered environments. Such environments contain rich features like crosswalks, grass, and curbs, which are easily interpretable by humans, but not by mobile robots. We aim to compute suitable trajectories that (1) satisfy the environment-specific traversability constraints and (2) generate human-like paths while navigating on crosswalks, sidewalks, etc. Our formulation uses a Conditional Variational Autoencoder (CVAE) generative model enhanced with traversability constraints to generate multiple candidate trajectories for global navigation. We develop a visual prompting approach and leverage the Visual Language Model's (VLM) zero-shot ability of semantic understanding and logical reasoning to choose the best trajectory given the contextual information about the task. We evaluate our method in various outdoor scenes with wheeled robots and compare the performance with other global navigation algorithms. In practice, we observe an average improvement of 20.81% in satisfying traversability constraints and 28.51% in terms of human-like navigation in four different outdoor navigation scenarios. |
| title | VL-TGS: Trajectory Generation and Selection using Vision Language Models in Mapless Outdoor Environments |
| topic | Robotics |
| url | https://arxiv.org/abs/2408.02454 |