28 December 2023 in IEEE Robotics & Automation Magazine
Recent interest in the control of underactuated robots has surged significantly due to the impressive athletic behaviors shown by robots developed by, e.g., Boston Dynamics ( https://www.bostondynamics.com ), Agility Robotics ( https://agilityrobotics.com/robots ), and the Massachusetts Institute of Technology [1]. This gives rise to the need for canonical robotic hardware setups for studying underactuation and comparing learning and control algorithms for their performance and robustness. Similar to OpenAIGym [2] and Stable Baselines [3], which provide simulated benchmarking environments and baselines for reinforcement learning algorithms, there is a need for benchmarking learning and control methods on real canonical hardware setups. To encourage reproducibility in robotics and artificial intelligence research, these hardware setups should be affordable and easy to manufacture with off-the-shelf components, and the accompanying software should be open source. Acrobots and pendubots are classical textbook examples of canonical underactuated systems with strong nonlinear dynamics, and their swing-up and upright balancing is considered a challenging control problem, especially on real hardware.
21 April 2023 in IEEE Robotics and Automation Letters
Brachiation is a dynamic, coordinated swinging maneuver of body and arms used by monkeys and apes to move between branches. As a unique underactuated mode of locomotion, it is interesting to study from a robotics perspective since it can broaden the deployment scenarios for humanoids and animaloids. While several brachiating robots of varying complexity have been proposed in the past, this letter presents the simplest possible prototype of a brachiation robot, using only a single actuator and unactuated grippers. The novel passive gripper design allows it to snap on and release from monkey bars, while guaranteeing well defined start and end poses of the swing. The brachiation behavior is realized in three different ways, using trajectory optimization via direct collocation and stabilization by a model-based time-varying linear quadratic regulator (TVLQR) or model-free proportional derivative (PD) control, as well as by a reinforcement learning (RL) based control policy. The three control schemes are compared in terms of robustness to disturbances, mass uncertainty, and energy consumption. The system design and controllers have been open-sourced. Due to its minimal and open design, the system can serve as a canonical underactuated platform for education and research.
15 December 2025 in IEEE Robotics & Automation Magazine
In robotics, many different approaches ranging from classical planning over optimal control to reinforcement learning (RL) are developed and borrowed from other fields to achieve reliable control in diverse tasks. To get a clear understanding of their individual strengths and weaknesses and their applicability in real-world robotic scenarios, it is important to benchmark and compare their performances not only in a simulation but also on real hardware. The second AI Olympics with RealAIGym competition was held at the 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024) to contribute to this cause and evaluate different controllers according to their ability to solve a dynamic control problem on an underactuated double-pendulum system (Figure 1) with chaotic dynamics. This article describes the four different RL methods submitted by the participating teams; presents their performance in the swing-up task on a real double pendulum, measured against various criteria; and discusses their transferability from simulation to real (sim-to-real) hardware and their robustness to external disturbances.
19 August 2024 in IEEE Robotics and Automation Letters
A great advantage of legged robots is their ability to operate on particularly difficult and obstructed terrain, which demands dynamic, robust, and precise movements. The study of obstacle courses provides invaluable insights into the challenges legged robots face, offering a controlled environment to assess and enhance their capabilities. Traversing it with a one-legged hopper introduces intricate challenges, such as planning over contacts and dealing with flight phases, which necessitates a sophisticated controller. A novel model predictive parkour controller is introduced, that finds an optimal path through a real-time changing obstacle course with mixed integer motion planning. The execution of this optimized path is then achieved through a state machine employing a PD control scheme with feedforward torques, ensuring robust and accurate performance.
17 October 2022 in Journal of Space Safety Engineering