Certifiable Robot Design Optimization using Differentiable Programming release_n6t53t5uhjdvrkk22iel3l276q

by Charles Dawson, Chuchu Fan

Released as a article .

2022  

Abstract

There is a growing need for computational tools to automatically design and verify autonomous systems, especially complex robotic systems involving perception, planning, control, and hardware in the autonomy stack. Differentiable programming has recently emerged as powerful tool for modeling and optimization. However, very few studies have been done to understand how differentiable programming can be used for robust, certifiable end-to-end design optimization. In this paper, we fill this gap by combining differentiable programming for robot design optimization with a novel statistical framework for certifying the robustness of optimized designs. Our framework can conduct end-to-end optimization and robustness certification for robotics systems, enabling simultaneous optimization of navigation, perception, planning, control, and hardware subsystems. Using simulation and hardware experiments, we show how our tool can be used to solve practical problems in robotics. First, we optimize sensor placements for robot navigation (a design with 5 subsystems and 6 tunable parameters) in under 5 minutes to achieve an 8.4x performance improvement compared to the initial design. Second, we solve a multi-agent collaborative manipulation task (3 subsystems and 454 parameters) in under an hour to achieve a 44% performance improvement over the initial design. We find that differentiable programming enables much faster (32% and 20x, respectively for each example) optimization than approximate gradient methods. We certify the robustness of each design and successfully deploy the optimized designs in hardware. An open-source implementation is available at https://github.com/MIT-REALM/architect
In text/plain format

Archived Files and Locations

application/pdf  8.7 MB
file_rzrthlxk7zbcpchrua53pjatbe
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2022-04-22
Version   v1
Language   en ?
arXiv  2204.10935v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 968fb33b-5d16-4675-9fe0-74d232504989
API URL: JSON