Generative AI in Embodied Systems: System-Level Analysis of Performance, Efficiency and Scalability
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916708955979776 |
|---|---|
| author | Wan, Zishen Qian, Jiayi Du, Yuhang Jabbour, Jason Du, Yilun Zhao, Yang Katie Raychowdhury, Arijit Krishna, Tushar Reddi, Vijay Janapa |
| author_facet | Wan, Zishen Qian, Jiayi Du, Yuhang Jabbour, Jason Du, Yilun Zhao, Yang Katie Raychowdhury, Arijit Krishna, Tushar Reddi, Vijay Janapa |
| contents | Embodied systems, where generative autonomous agents engage with the physical world through integrated perception, cognition, action, and advanced reasoning powered by large language models (LLMs), hold immense potential for addressing complex, long-horizon, multi-objective tasks in real-world environments. However, deploying these systems remains challenging due to prolonged runtime latency, limited scalability, and heightened sensitivity, leading to significant system inefficiencies.
In this paper, we aim to understand the workload characteristics of embodied agent systems and explore optimization solutions. We systematically categorize these systems into four paradigms and conduct benchmarking studies to evaluate their task performance and system efficiency across various modules, agent scales, and embodied tasks. Our benchmarking studies uncover critical challenges, such as prolonged planning and communication latency, redundant agent interactions, complex low-level control mechanisms, memory inconsistencies, exploding prompt lengths, sensitivity to self-correction and execution, sharp declines in success rates, and reduced collaboration efficiency as agent numbers increase. Leveraging these profiling insights, we suggest system optimization strategies to improve the performance, efficiency, and scalability of embodied agents across different paradigms. This paper presents the first system-level analysis of embodied AI agents, and explores opportunities for advancing future embodied system design. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_18945 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Generative AI in Embodied Systems: System-Level Analysis of Performance, Efficiency and Scalability Wan, Zishen Qian, Jiayi Du, Yuhang Jabbour, Jason Du, Yilun Zhao, Yang Katie Raychowdhury, Arijit Krishna, Tushar Reddi, Vijay Janapa Robotics Embodied systems, where generative autonomous agents engage with the physical world through integrated perception, cognition, action, and advanced reasoning powered by large language models (LLMs), hold immense potential for addressing complex, long-horizon, multi-objective tasks in real-world environments. However, deploying these systems remains challenging due to prolonged runtime latency, limited scalability, and heightened sensitivity, leading to significant system inefficiencies. In this paper, we aim to understand the workload characteristics of embodied agent systems and explore optimization solutions. We systematically categorize these systems into four paradigms and conduct benchmarking studies to evaluate their task performance and system efficiency across various modules, agent scales, and embodied tasks. Our benchmarking studies uncover critical challenges, such as prolonged planning and communication latency, redundant agent interactions, complex low-level control mechanisms, memory inconsistencies, exploding prompt lengths, sensitivity to self-correction and execution, sharp declines in success rates, and reduced collaboration efficiency as agent numbers increase. Leveraging these profiling insights, we suggest system optimization strategies to improve the performance, efficiency, and scalability of embodied agents across different paradigms. This paper presents the first system-level analysis of embodied AI agents, and explores opportunities for advancing future embodied system design. |
| title | Generative AI in Embodied Systems: System-Level Analysis of Performance, Efficiency and Scalability |
| topic | Robotics |
| url | https://arxiv.org/abs/2504.18945 |