Deluca -- A Differentiable Control Library: Environments, Methods, and Benchmarking
This provides a practical tool for researchers in control systems and robotics, though it is incremental as it builds on existing differentiable simulation concepts.
The authors introduced Deluca, an open-source library of differentiable physics and robotics environments that enables auto-differentiation through simulation dynamics for fast controller training, and demonstrated its utility with applications including a medical ventilator simulator and adaptive control methods.
We present an open-source library of natively differentiable physics and robotics environments, accompanied by gradient-based control methods and a benchmark-ing suite. The introduced environments allow auto-differentiation through the simulation dynamics, and thereby permit fast training of controllers. The library features several popular environments, including classical control settings from OpenAI Gym. We also provide a novel differentiable environment, based on deep neural networks, that simulates medical ventilation. We give several use-cases of new scientific results obtained using the library. This includes a medical ventilator simulator and controller, an adaptive control method for time-varying linear dynamical systems, and new gradient-based methods for control of linear dynamical systems with adversarial perturbations.