Identifying the physical properties of the surrounding environment is essential for robotic locomotion and navigation to deal with non-geometric hazards, such as slippery and deformable terrains. It would be of great benefit for robots to anticipate these extreme physical properties before contact; however, estimating environmental physical parameters from vision is still an open challenge. Animals can achieve this by using their prior experience and knowledge of what they have seen and how it felt. In this work, we propose a cross-modal selfsupervised learning framework for vision-based environmental physical parameter estimation, which paves the way for future physical-property-aware locomotion and navigation. We bridge the gap between existing policies trained in simulation and identification of physical terrain parameters from vision. We propose to train a physical decoder in simulation to predict friction and stiffness from multi-modal input. The trained network allows the labeling of real-world images with physical parameters in a self-supervised manner to further train a visual network during deployment, which can densely predict the friction and stiffness from image data. We validate our physical decoder in simulation and the real world using a quadruped ANYmal robot, outperforming an existing baseline method. We show that our visual network can predict the physical properties in indoor and outdoor experiments while allowing fast adaptation to new environments
24 June 2019 in IEEE Robotics and Automation Letters
Lower-limb exoskeletons have shown increasing potential to augment human performance in many locomotion tasks. However, most lower-limb exoskeletons use highly-geared, non-back-drivable actuators with limited power and force bandwidth in order to be light enough to be carried without metabolic penalty. Moreover, they rely on controllers that depend on past motion history to assist the user, which limits the multifunctional capabilities of exoskeletons. Here we study the potential of delocalized magnetorheological (MR) clutches to provide transparent but yet powerful multifunctional exoskeleton assistance. A single high-speed, lightweight motor is coupled with two MR clutches that modulate the plantar-flexion torque at each ankle. The exoskeleton is controlled by a state map controller that can assist users in real time while walking, jumping and landing. Results confirm the potential of the magnetorheological actuation approach by demonstrating instantaneous adaptation to transient walking and by producing a maximal torque of 90 Nm per ankle with a total power of 1.4 kW when jumping. The system also actively braked landing impact and achieved multifunctional assistance in a sequence of walking, jumping and landing. With a total mass of 6.2 kg including 0.9 kg on each leg, the system reduces metabolic cost of walking by 5.6% on average with tethered electronics and power supply.
29 June 2020 in IEEE Robotics and Automation Letters
The parallelism afforded by GPUs presents significant advantages in training controllers through reinforcement learning (RL). However, integrating model-based optimization into this process remains challenging due to the complexity of formulating and solving optimization problems across thousands of instances. In this work, we present CusADi , an extension of the casadi symbolic framework to support the parallelization of arbitrary closed-form expressions on GPUs with CUDA . We also formulate a closed-form approximation for solving general optimal control problems, enabling large-scale parallelization and evaluation of MPC controllers. Our results show a ten-fold speedup relative to similar MPC implementation on the CPU, and we demonstrate the use of CusADi for various applications, including parallel simulation, parameter sweeps, and policy training.
This paper proposes a novel orientation-aware model predictive control (MPC) for dynamic humanoid walking that can plan footstep locations online. Instead of a point-mass model, this work uses the augmented single rigid body model (aSRBM) to enable the MPC to leverage orientation dynamics and stepping strategy within a unified optimization framework. With the footstep location as part of the decision variables in the aSRBM, the MPC can reason about stepping within the kinematic constraints. A task-space controller (TSC) tracks the body pose and swing leg references output from the MPC, while exploiting the full-order dynamics of the humanoid. The proposed control framework is suitable for real-time applications since both MPC and TSC are formulated as quadratic programs. Simulation investigations show that the orientation-aware MPC-based framework is more robust against external torque disturbance compared to state-of-the-art controllers using the point mass model, especially when the torso undergoes large angular excursion. The same control framework can also enable the MIT Humanoid to overcome uneven terrains, such as traversing a wave field.
This work combines control barrier functions (CBFs) with a whole-body controller to enable self-collision avoidance for the MIT Humanoid. Existing reactive controllers for self-collision avoidance cannot guarantee collision-free trajectories as they do not leverage the robot's full dynamics, thus compromising kinematic feasibility. In comparison, the proposed CBF-WBC controller can reason about the robot's underactuated dynamics in real-time to guarantee collision-free motions. The effectiveness of this approach is validated in simulation. First, a simple hand-reaching experiment shows that the CBF-WBC enables the robot's hand to deviate from an infeasible reference trajectory to avoid self-collisions. Second, the CBF-WBC is combined with a linear model predictive controller (LMPC) designed for dynamic locomotion, and the CBF-WBC is used to track the LMPC predictions. Walking experiments show that adding CBFs avoids leg self-collisions when the footstep location or swing trajectory provided by the high-level planner are infeasible for the real robot, and generates feasible arm motions that improve disturbance recovery.