Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2511.04769 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912692848033792 |
|---|---|
| author | Nguyen, Phat Wang, Tsun-Hsuan Hong, Zhang-Wei Aasi, Erfan Silva, Andrew Rosman, Guy Karaman, Sertac Rus, Daniela |
| author_facet | Nguyen, Phat Wang, Tsun-Hsuan Hong, Zhang-Wei Aasi, Erfan Silva, Andrew Rosman, Guy Karaman, Sertac Rus, Daniela |
| contents | Simulation plays a key role in scaling robot learning and validating policies, but constructing simulations remains a labor-intensive process. This paper introduces ReGen, a generative simulation framework that automates simulation design via inverse design. Given a robot's behavior -- such as a motion trajectory or an objective function -- and its textual description, ReGen infers plausible scenarios and environments that could have caused the behavior. ReGen leverages large language models to synthesize scenarios by expanding a directed graph that encodes cause-and-effect relationships, relevant entities, and their properties. This structured graph is then translated into a symbolic program, which configures and executes a robot simulation environment. Our framework supports (i) augmenting simulations based on ego-agent behaviors, (ii) controllable, counterfactual scenario generation, (iii) reasoning about agent cognition and mental states, and (iv) reasoning with distinct sensing modalities, such as braking due to faulty GPS signals. We demonstrate ReGen in autonomous driving and robot manipulation tasks, generating more diverse, complex simulated environments compared to existing simulations with high success rates, and enabling controllable generation for corner cases. This approach enhances the validation of robot policies and supports data or simulation augmentation, advancing scalable robot learning for improved generalization and robustness. We provide code and example videos at: https://regen-sim.github.io/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_04769 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ReGen: Generative Robot Simulation via Inverse Design Nguyen, Phat Wang, Tsun-Hsuan Hong, Zhang-Wei Aasi, Erfan Silva, Andrew Rosman, Guy Karaman, Sertac Rus, Daniela Robotics Simulation plays a key role in scaling robot learning and validating policies, but constructing simulations remains a labor-intensive process. This paper introduces ReGen, a generative simulation framework that automates simulation design via inverse design. Given a robot's behavior -- such as a motion trajectory or an objective function -- and its textual description, ReGen infers plausible scenarios and environments that could have caused the behavior. ReGen leverages large language models to synthesize scenarios by expanding a directed graph that encodes cause-and-effect relationships, relevant entities, and their properties. This structured graph is then translated into a symbolic program, which configures and executes a robot simulation environment. Our framework supports (i) augmenting simulations based on ego-agent behaviors, (ii) controllable, counterfactual scenario generation, (iii) reasoning about agent cognition and mental states, and (iv) reasoning with distinct sensing modalities, such as braking due to faulty GPS signals. We demonstrate ReGen in autonomous driving and robot manipulation tasks, generating more diverse, complex simulated environments compared to existing simulations with high success rates, and enabling controllable generation for corner cases. This approach enhances the validation of robot policies and supports data or simulation augmentation, advancing scalable robot learning for improved generalization and robustness. We provide code and example videos at: https://regen-sim.github.io/ |
| title | ReGen: Generative Robot Simulation via Inverse Design |
| topic | Robotics |
| url | https://arxiv.org/abs/2511.04769 |