Deep Lagrangian Networks for end-to-end learning of energy-based control for under-actuated systems
Applying Deep Learning to control has a lot of potential for enabling the intelligent design of robot control laws. Unfortunately common deep learning approaches to control, such as deep reinforcement learning, require an unrealistic amount of interaction with the real system, do not yield any performance guarantees, and do not make good use of extensive insights from model-based control. In particular, common black-box approaches -- that abandon all insight from control -- are not suitable for complex robot systems. We propose a deep control approach as a bridge between the solid theoretical foundations of energy-based control and the flexibility of deep learning. To accomplish this goal, we extend Deep Lagrangian Networks (DeLaN) to not only adhere to Lagrangian Mechanics but also ensure conservation of energy and passivity of the learned representation. This novel extension is embedded within generic model-based control laws to enable energy control of under-actuated systems. The resulting DeLaN for energy control (DeLaN 4EC) is the first model learning approach using generic function approximation that is capable of learning energy control. DeLaN 4EC exhibits excellent real-time control on the physical Furuta Pendulum and learns to swing-up the pendulum while the control law using system identification does not.
Code (1)
Tasks
Deep LearningDeep Reinforcement LearningReinforcement LearningSimilar Papers 제목 키워드 기반
KeyCLD: Learning Constrained Lagrangian Dynamics in Keypoint Coordinates from Images
We present KeyCLD, a framework to learn Lagrangian dynamics from images. Learned keypoints represent semantic landmarks in images and can directly represent state dynamics. We show that interpreting this state as Cartesi…
AcrobotvalidReduced-order Control and Geometric Structure of Learned Lagrangian Latent Dynamics
Model-based controllers can offer strong guarantees on stability and convergence by relying on physically accurate dynamic models. However, these are rarely available for high-dimensional mechanical systems such as defor…
Total energy-shaping control for mechanical systems via Control-by-Interconnection
Application of IDA-PBC to mechanical systems has received much attention in recent decades, but its application is still limited by the solvability of the so-called matching conditions. In this work, it is shown that tot…
AcrobotSymmetries and periodic orbits in simple hybrid Routhian systems
Symmetries are ubiquitous in a wide range of nonlinear systems. Particularly in systems whose dynamics are determined by a Lagrangian or Hamiltonian function. For hybrid systems which possess a continuous-time dynamics d…
Neural Autoencoder-Based Structure-Preserving Model Order Reduction and Control Design for High-Dimensional Physical Systems
This work concerns control-oriented and structure-preserving learning of low-dimensional approximations of high-dimensional physical systems, with a focus on mechanical systems. We investigate the integration of neural a…