论文标题
可认证的机器人设计优化的优化
Certifiable Robot Design Optimization using Differentiable Programming
论文作者
论文摘要
越来越需要计算工具来自动设计和验证自主系统的自主系统，尤其是涉及自治堆栈中感知，计划，控制和硬件的复杂机器人系统。可区分的编程最近成为建模和优化的强大工具。但是，很少进行研究来了解如何将可区分的编程用于可靠的可认证的端到端设计优化。在本文中，我们通过将可区别的编程与机器人设计优化的可区分编程与一个新颖的统计框架相结合，以证明优化设计的鲁棒性，以填补这一空白。我们的框架可以对机器人系统进行端到端的优化和鲁棒性认证，从而可以同时优化导航，感知，计划，控制和硬件子系统。 使用仿真和硬件实验，我们展示了如何使用工具来解决机器人技术中的实际问题。首先，我们在5分钟内优化机器人导航（具有5个子系统和6个可调参数的设计）的传感器位置，与初始设计相比，可以提高8.4倍的性能。其次，我们在一个小时内解决了一项多代理协作操作任务（3个子系统和454个参数），以在初始设计中实现44％的性能提高。我们发现，比近似梯度方法比近似梯度方法更快地（对于每个示例，分别为32％和20倍）可以更快地（分别为32％和20倍）。我们证明了每种设计的鲁棒性，并在硬件中成功部署了优化的设计。可以从https://github.com/mit-realm/architect获得开源实现
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
