iMotion-LLM: Instruction-Conditioned Trajectory Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908694513451008 |
|---|---|
| author | Felemban, Abdulwahab Hroub, Nussair Ding, Jian Abdelrahman, Eslam Shen, Xiaoqian Mohamed, Abduallah Elhoseiny, Mohamed |
| author_facet | Felemban, Abdulwahab Hroub, Nussair Ding, Jian Abdelrahman, Eslam Shen, Xiaoqian Mohamed, Abduallah Elhoseiny, Mohamed |
| contents | We introduce iMotion-LLM, a large language model (LLM) integrated with trajectory prediction modules for interactive motion generation. Unlike conventional approaches, it generates feasible, safety-aligned trajectories based on textual instructions, enabling adaptable and context-aware driving behavior. It combines an encoder-decoder multimodal trajectory prediction model with a pre-trained LLM fine-tuned using LoRA, projecting scene features into the LLM input space and mapping special tokens to a trajectory decoder for text-based interaction and interpretable driving. To support this framework, we introduce two datasets: 1) InstructWaymo, an extension of the Waymo Open Motion Dataset with direction-based motion instructions, and 2) Open-Vocabulary InstructNuPlan, which features safety-aligned instruction-caption pairs and corresponding safe trajectory scenarios. Our experiments validate that instruction conditioning enables trajectory generation that follows the intended condition. iMotion-LLM demonstrates strong contextual comprehension, achieving 84% average accuracy in direction feasibility detection and 96% average accuracy in safety evaluation of open-vocabulary instructions. This work lays the foundation for text-guided motion generation in autonomous driving, supporting simulated data generation, model interpretability, and robust safety alignment testing for trajectory generation models. Our code, pre-trained model, and datasets are available at: https://vision-cair.github.io/iMotion-LLM/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_06211 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | iMotion-LLM: Instruction-Conditioned Trajectory Generation Felemban, Abdulwahab Hroub, Nussair Ding, Jian Abdelrahman, Eslam Shen, Xiaoqian Mohamed, Abduallah Elhoseiny, Mohamed Computer Vision and Pattern Recognition We introduce iMotion-LLM, a large language model (LLM) integrated with trajectory prediction modules for interactive motion generation. Unlike conventional approaches, it generates feasible, safety-aligned trajectories based on textual instructions, enabling adaptable and context-aware driving behavior. It combines an encoder-decoder multimodal trajectory prediction model with a pre-trained LLM fine-tuned using LoRA, projecting scene features into the LLM input space and mapping special tokens to a trajectory decoder for text-based interaction and interpretable driving. To support this framework, we introduce two datasets: 1) InstructWaymo, an extension of the Waymo Open Motion Dataset with direction-based motion instructions, and 2) Open-Vocabulary InstructNuPlan, which features safety-aligned instruction-caption pairs and corresponding safe trajectory scenarios. Our experiments validate that instruction conditioning enables trajectory generation that follows the intended condition. iMotion-LLM demonstrates strong contextual comprehension, achieving 84% average accuracy in direction feasibility detection and 96% average accuracy in safety evaluation of open-vocabulary instructions. This work lays the foundation for text-guided motion generation in autonomous driving, supporting simulated data generation, model interpretability, and robust safety alignment testing for trajectory generation models. Our code, pre-trained model, and datasets are available at: https://vision-cair.github.io/iMotion-LLM/. |
| title | iMotion-LLM: Instruction-Conditioned Trajectory Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.06211 |