Boston Dynamics (United States)

The tremendous success of behavior cloning (BC) in robotic manipulation has been largely confined to tasks where demonstrations can be effectively collected through human teleoperation. However, demonstrations for contact-rich manipulation tasks that require complex coordination of multiple contacts are difficult to collect due to the limitations of current teleoperation interfaces. We investigate how to leverage model-based planning and optimization to generate training data for contact-rich dexterous manipulation tasks. Our analysis reveals that popular sampling-based planners like rapidly exploring random tree (RRT), while efficient for motion planning, produce demonstrations with unfavorably high entropy. This motivates modifications to our data generation pipeline that prioritizes demonstration consistency while maintaining solution coverage. Combined with a diffusion-based goal-conditioned BC approach, our method enables effective policy learning and zero-shot transfer to hardware for two challenging contact-rich manipulation tasks. Video: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://youtu.be/CxgjJmiiEhI</uri>

Cross-pose estimation between rigid objects is a fundamental building block for robotic applications. In this paper, we propose a new cross-pose estimation method that predicts correspondences on a set level as opposed to a point level. This contrasts methods that predict cross-pose from per-point correspondences, which can encounter optimization problems for objects with symmetries, since each point may have multiple valid correspondences. Our method, SCAlign, consists of a Set Correspondence Network (SCN) which predicts these sets and their correspondences, and an alignment module to compute their relative cross-pose. Taking point clouds of two objects as input, SCN predicts a set label for each point such that such that points that share a set label form a cross object correspondence. The alignment module then computes the cross-pose as the SE(3) transformation that aligns these set correspondences. We compare SCAlign against other cross-pose estimation baselines on a synthetically generated dataset, SynWidth, which contains randomly generated width-mate objects with symmetric or near-symmetric intercepts. SCAlign significantly outperforms the baselines on this challenging dataset. Additionally, we show that set correspondences can be leveraged to distinguish positive and negative matches between pegs and holes. Robot experiments further validate the practical application of this approach.

We develop an approach to improve the learning capabilities of robotic systems by combining learned predictive models with experience-based state-action policy mappings. Predictive models provide an understanding of the task and the dynamics, while experience-based (model-free) policy mappings encode favorable actions that override planned actions. We refer to our approach of systematically combining model-based and model-free learning methods as hybrid learning. Our approach efficiently learns motor skills and improves the performance of predictive models and experience-based policies. Moreover, our approach enables policies (both model-based and model-free) to be updated using any off-policy reinforcement learning method. We derive a deterministic method of hybrid learning by optimally switching between learning modalities. We adapt our method to a stochastic variation that relaxes some of the key assumptions in the original derivation. Our deterministic and stochastic variations are tested on a variety of robot control benchmark tasks in simulation as well as a hardware manipulation task. We extend our approach for use with imitation learning methods, where experience is provided through demonstrations, and we test the expanded capability with a real-world pick-and-place task. The results show that our method is capable of improving the performance and sample efficiency of learning motor skills in a variety of experimental domains.

We describe the design and implementation of a motion control server that proved crucial to the safe assembly and validation of Mars 2020 hardware in the absence of flight avionics.

We analyze the existence and stability of phase-locked states of neurons coupled electrically with gap junctions. We show that spike shape and size, along with driving current (which affects network frequency), play a large role in which phase-locked modes exist and are stable. Our theory makes predictions about biophysical models using spikes of different shapes, and we present simulations to confirm the predictions. We also analyze a large system of all-to-all coupled neurons and show that the splay-phase state can exist only for a certain range of frequencies.

We have developed an interactive virtual reality (VR) surgical simulator for the training and assessment of suturing technique in the context of end-to-end anastomosis. The surgical simulator is comprised of surgical tools with force feedback, a 3D visual display of the simulated surgical field, physics-based computer simulations of the tissues and tools, and software to measure and evaluate the trainee’s performance. This study uses the simulator to compare the skills of experienced vascular surgeons to medical students. Eight parameters were measured to evaluate performance during VR suturing tasks. The data indicate significant differences between surgeon and non-surgeon performance, as well as improvement in performance with training. We believe that this study offers support for the use of virtual reality surgical simulators to augment surgical skill assessment and training.