Search for: All records

Learning policies for contact-rich manipulation is a challenging problem due to the presence of multiple contact modes with different dynamics, which complicates state and action exploration. Contact-rich motion planning uses simplified dynamics to reduce the search space dimension, but the found plans are then difficult to execute under the true object-manipulator dynamics. This paper presents an algorithm for learning controllers based on guided policy search, where motion plans based on simplified dynamics define rewards and sampling distributions for policy gradient-based learning. We demonstrate that our guided policy search method improves the ability to learn manipulation controllers, through a task involving pushing a box over a step. 

In this work, we discuss the modeling, control, and implementation of a rimless wheel with a torso. We derive and compare two control methodologies: a discrete-time controller (DT) that updates the controls once-per-step and a continuous-time controller (CT) that updates gains continuously. For the discrete controller, we use least-squares estimation method to approximate the Poincare ́ map on a certain section and use discrete- linear-quadratic-regulator (DQLR) to stabilize a (closed-form) linearization of this map. For the continuous controller, we introduce moving Poincare ́ sections and stabilize the transverse dynamics along these moving sections. For both controllers, we estimate the region of attraction of the closed-loop system using sum-of-squares methods. Analysis of the impact map yields a refinement of the controller that stabilizes a steady-state walking gait with minimal energy loss. We present both simulation and experimental results that support the validity of the proposed approaches. We find that the CT controller has a larger region of attraction and smoother stabilization as compared with the DT controller. 

Quantitative volumetric assessment of filamentous actin (F‐actin) fibers remains challenging due to their interconnected nature, leading researchers to utilize threshold‐based or qualitative measurement methods with poor reproducibility. Herein, a novel machine learning‐based methodology is introduced for accurate quantification and reconstruction of nuclei‐associated F‐actin. Utilizing a convolutional neural network (CNN), actin filaments and nuclei from 3D confocal microscopy images are segmented and then each fiber is reconstructed by connecting intersecting contours on cross‐sectional slices. This allows measurement of the total number of actin filaments and individual actin filament length and volume in a reproducible fashion. Focusing on the role of F‐actin in supporting nucleocytoskeletal connectivity, apical F‐actin, basal F‐actin, and nuclear architecture in mesenchymal stem cells (MSCs) are quantified following the disruption of the linker of nucleoskeleton and cytoskeleton (LINC) complexes. Disabling LINC in MSCs generates F‐actin disorganization at the nuclear envelope characterized by shorter length and volume of actin fibers contributing a less elongated nuclear shape. The findings not only present a new tool for mechanobiology but introduce a novel pipeline for developing realistic computational models based on quantitative measures of F‐actin.