Guided policy search is a popular approach for training controllers for high-dimensional systems, but it has a number of pitfalls. Non-convex trajectory optimization has local minima, and non-uniqueness in the optimal policy itself can mean that independently-optimized samples do not describe a coherent policy from which to train. We introduce LVIS, which circumvents the issue of local minima through global mixed-integer optimization and the issue of non-uniqueness through learning the optimal value function rather than the optimal policy. To avoid the expense of solving the mixed-integer programs to full global optimality, we instead solve them only partially, extracting intervals containing the true cost-to-go from early termination of the branch-and-bound algorithm. These interval samples are used to weakly supervise the training of a neural net which approximates the true cost-to-go. Online, we use that learned cost-to-go as the terminal cost of a one-step model-predictive controller, which we solve via a small mixed-integer optimization. We demonstrate LVIS on piecewise affine models of a cart-pole system with walls and a planar humanoid robot and show that it can be applied to a fundamentally hard problem in feedback control-control through contact.

Robotics applications often suffer from the `two-language problem', requiring a low-level language for performance-sensitive components and a high-level language for interactivity and experimentation, which tends to increase software complexity. We demonstrate the use of the Julia programming language to solve this problem by being fast enough for online control of a humanoid robot and flexible enough for prototyping. We present several Julia packages developed by the authors, which together enable roughly 2× realtime simulation of the Boston Dynamics Atlas humanoid robot balancing on flat ground using a quadratic-programming-based controller. Benchmarks show a sufficiently low variation in control frequency to make deployment on the physical robot feasible. We also show that Julia's naturally generic programming style results in versatile packages that are easy to compose and adapt to a wide variety of computational tasks in robotics.

Rigid body dynamics calculations are needed for many tasks in robotics, including online control. While there currently exist several competing software implementations that are sufficient for use in traditional control approaches, emerging sophisticated motion control techniques such as nonlinear model predictive control demand orders of magnitude more frequent dynamics calculations. Current software solutions are not fast enough to meet that demand for complex robots. The goal of this work is to examine the performance of current dynamics software libraries in detail. In this paper, we (i) survey current state-of-the-art software implementations of the key rigid body dynamics algorithms (RBDL, Pinocchio, Rigid-BodyDynamics.jl, and RobCoGen), (ii) establish a methodology for benchmarking these algorithms, and (iii) characterize their performance through real measurements taken on a modern hardware platform. With this analysis, we aim to provide direction for future improvements that will need to be made to enable emerging techniques for real-time robot motion control. To this end, we are also releasing our suite of benchmarks to enable others to help contribute to this important task.

This paper works with the concept of Divergent Component of Motion (DCM), also called `(instantaneous) Capture Point'. We present two real-time DCM trajectory generators for uneven (three-dimensional) ground surfaces, which lead to continuous leg (and corresponding ground reaction) force profiles and facilitate the use of toe-off motion during double support. Thus, the resulting DCM trajectories are well suited for real-world robots and allow for increased step length and step height. The performance of the proposed methods was tested in numerous simulations and experiments on IHMC's Atlas robot and DLR's humanoid robot TORO.

This video highlights work to date on the Yobotics-IHMC lower body humanoid robot. The robot is a twelve degree-of-freedom robot with force controllable series elastic actuators at each degree of freedom. Control algorithms utilize virtual model control, and foot placement is determined using capture regions. The robot can recover from moderate disturbances and walk on flat ground. Ongoing work is focused on improving robustness to disturbances, walking more quickly and efficiently, and walking over rough terrain.