Alexander Leonessa

Ruturaj Sambhus, Aydin Gokce, Stephen Welch et al.

Many state-of-the art robotic applications utilize series elastic actuators (SEAs) with closed-loop force control to achieve complex tasks such as walking, lifting, and manipulation. Model-free PID control methods are more prone to instability due to nonlinearities in the SEA where cascaded model-based robust controllers can remove these effects to achieve stable force control. However, these model-based methods require detailed investigations to characterize the system accurately. Deep reinforcement learning (DRL) has proved to be an effective model-free method for continuous control tasks, where few works deal with hardware learning. This paper describes the training process of a DRL policy on hardware of an SEA pendulum system for tracking force control trajectories from 0.05 - 0.35 Hz at 50 N amplitude using the Proximal Policy Optimization (PPO) algorithm. Safety mechanisms are developed and utilized for training the policy for 12 hours (overnight) without an operator present within the full 21 hours training period. The tracking performance is evaluated showing improvements of $25$ N in mean absolute error when comparing the first 18 min. of training to the full 21 hours for a 50 N amplitude, 0.1 Hz sinusoid desired force trajectory. Finally, the DRL policy exhibits better tracking and stability margins when compared to a model-free PID controller for a 50 N chirp force trajectory.

Negin Nikafrooz, Zachary Fuge, Alexander Leonessa

Detecting and preventing slip is a major challenge in robotic hand operation, underpinning the robot's ability to perform safe and reliable grasps. Using the robotic hand design from the authors' earlier work, a sensing and control strategy is proposed here to prevent object slippage. The robotic hand is cable-driven, single-actuated, has five fingers, and is capable of replicating most human hand motions. The slip sensing approach utilizes a piezoelectric vibration sensor, namely, polyvinylidene fluoride (PVDF), which is a flexible, thin, cheap, and highly sensitive material. The power of the filtered PVDF signal is shown to exhibit identifiable signatures during slip, thus providing a suitable slip detection mechanism. Using the PVDF feedback, an integral controller is implemented to prevent the grasped object from falling and ensure a safe, powerful, and reliable grasp. The extension movement of the robotic hand is controlled using a bend sensor, through a proportional-integral (PI) controller. The robotic hand weights 338 gr. The functionality and robustness of the proposed slip-detection sensory system and control logic implementation are evaluated through experiments.

Robert J. Griffin, Georg Wiedebach, Sylvain Bertrand et al.

We present an approach for achieving a natural, efficient gait on bipedal robots using straightened legs and toe-off. Our algorithm avoids complex height planning by allowing a whole-body controller to determine the straightest possible leg configuration at run-time. The controller solutions are biased towards a straight leg configuration by projecting leg joint angle objectives into the null-space of the other quadratic program motion objectives. To allow the legs to remain straight throughout the gait, toe-off was utilized to increase the kinematic reachability of the legs. The toe-off motion is achieved through underconstraining the foot position, allowing it to emerge naturally. We applied this approach of under-specifying the motion objectives to the Atlas humanoid, allowing it to walk over a variety of terrain. We present both experimental and simulation results and discuss performance limitations and potential improvements.

Gordon Christie, Adam Shoemaker, Kevin Kochersberger et al.

Autonomously searching for hazardous radiation sources requires the ability of the aerial and ground systems to understand the scene they are scouting. In this paper, we present systems, algorithms, and experiments to perform radiation search using unmanned aerial vehicles (UAV) and unmanned ground vehicles (UGV) by employing semantic scene segmentation. The aerial data is used to identify radiological points of interest, generate an orthophoto along with a digital elevation model (DEM) of the scene, and perform semantic segmentation to assign a category (e.g. road, grass) to each pixel in the orthophoto. We perform semantic segmentation by training a model on a dataset of images we collected and annotated, using the model to perform inference on images of the test area unseen to the model, and then refining the results with the DEM to better reason about category predictions at each pixel. We then use all of these outputs to plan a path for a UGV carrying a LiDAR to map the environment and avoid obstacles not present during the flight, and a radiation detector to collect more precise radiation measurements from the ground. Results of the analysis for each scenario tested favorably. We also note that our approach is general and has the potential to work for a variety of different sensing tasks.