λ: A Benchmark for Data-Efficiency in Long-Horizon Indoor Mobile Manipulation Robotics
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_ | 1866913970506432512 |
|---|---|
| author | Jaafar, Ahmed Raman, Shreyas Sundara Harithas, Sudarshan Wei, Yichen Juliani, Sofia Wernerfelt, Anneke Quartey, Benedict Idrees, Ifrah Liu, Jason Xinyu Tellex, Stefanie |
| author_facet | Jaafar, Ahmed Raman, Shreyas Sundara Harithas, Sudarshan Wei, Yichen Juliani, Sofia Wernerfelt, Anneke Quartey, Benedict Idrees, Ifrah Liu, Jason Xinyu Tellex, Stefanie |
| contents | Learning to execute long-horizon mobile manipulation tasks is crucial for advancing robotics in household and workplace settings. However, current approaches are typically data-inefficient, underscoring the need for improved models that require realistically sized benchmarks to evaluate their efficiency. To address this, we introduce the LAMBDA (λ) benchmark-Long-horizon Actions for Mobile-manipulation Benchmarking of Directed Activities-which evaluates the data efficiency of models on language-conditioned, long-horizon, multi-room, multi-floor, pick-and-place tasks using a dataset of manageable size, more feasible for collection. Our benchmark includes 571 human-collected demonstrations that provide realism and diversity in simulated and real-world settings. Unlike planner-generated data, these trajectories offer natural variability and replay-verifiability, ensuring robust learning and evaluation. We leverage λ to benchmark current end-to-end learning methods and a modular neuro-symbolic approach that combines foundation models with task and motion planning. We find that learning methods, even when pretrained, yield lower success rates, while a neuro-symbolic method performs significantly better and requires less data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_05313 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | λ: A Benchmark for Data-Efficiency in Long-Horizon Indoor Mobile Manipulation Robotics Jaafar, Ahmed Raman, Shreyas Sundara Harithas, Sudarshan Wei, Yichen Juliani, Sofia Wernerfelt, Anneke Quartey, Benedict Idrees, Ifrah Liu, Jason Xinyu Tellex, Stefanie Robotics Artificial Intelligence Machine Learning Learning to execute long-horizon mobile manipulation tasks is crucial for advancing robotics in household and workplace settings. However, current approaches are typically data-inefficient, underscoring the need for improved models that require realistically sized benchmarks to evaluate their efficiency. To address this, we introduce the LAMBDA (λ) benchmark-Long-horizon Actions for Mobile-manipulation Benchmarking of Directed Activities-which evaluates the data efficiency of models on language-conditioned, long-horizon, multi-room, multi-floor, pick-and-place tasks using a dataset of manageable size, more feasible for collection. Our benchmark includes 571 human-collected demonstrations that provide realism and diversity in simulated and real-world settings. Unlike planner-generated data, these trajectories offer natural variability and replay-verifiability, ensuring robust learning and evaluation. We leverage λ to benchmark current end-to-end learning methods and a modular neuro-symbolic approach that combines foundation models with task and motion planning. We find that learning methods, even when pretrained, yield lower success rates, while a neuro-symbolic method performs significantly better and requires less data. |
| title | λ: A Benchmark for Data-Efficiency in Long-Horizon Indoor Mobile Manipulation Robotics |
| topic | Robotics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2412.05313 |