This paper presents a method to learn hand-object interaction prior for reconstructing a 3D hand-object scene from a single RGB image. The inference as well as training-data generation for 3D hand-object scene reconstruction is challenging due to the depth ambiguity of a single image and occlusions by the hand and object. We turn this challenge into an opportunity by utilizing the hand shape to constrain the possible relative configuration of the hand and object geometry. We design a generalizable implicit function, HandNeRF, that explicitly encodes the correlation of the 3D hand shape features and 2D object features to predict the hand and object scene geometry. With experiments on real-world datasets, we show that HandNeRF can reconstruct hand-object scenes of novel grasp configurations more accurately than comparable methods. Moreover, we demonstrate that object reconstruction from HandNeRF ensures more accurate execution of downstream tasks, such as grasping for robotic hand-over.

We consider the problem of closed-loop robotic grasping and present a novel planner which uses Visual Feedback and an uncertainty-aware Adaptive Sampling strategy (VFAS) to close the loop. At each iteration, our method VFAS-Grasp builds a set of candidate grasps by generating random perturbations of a seed grasp. The candidates are then scored using a novel metric which combines a learned grasp-quality estimator, the uncertainty in the estimate and the distance from the seed proposal to promote temporal consistency. Additionally, we present two mechanisms to improve the efficiency of our sampling strategy: We dynamically scale the sampling region size and number of samples in it based on past grasp scores. We also leverage a motion vector field estimator to shift the center of our sampling region. We demonstrate that our algorithm can run in real time (20 Hz) and is capable of improving grasp performance for static scenes by refining the initial grasp proposal. We also show that it can enable grasping of slow moving objects, such as those encountered during human to robot handover. Video: https://youtu.be/8DRe2OFlf7o

Laser speckle contrast imaging (LSCI) is widely used for in vivo real-time detection and analysis of local blood flow microcirculation due to its non-invasive ability and excellent spatial and temporal resolution. However, vascular segmentation of LSCI images still faces a lot of difficulties due to numerous specific noises caused by the complexity of blood microcirculation's structure and irregular vascular aberrations in diseased regions. In addition, the difficulties of LSCI image data annotation have hindered the application of deep learning methods based on supervised learning in the field of LSCI image vascular segmentation. To tackle these difficulties, we propose a robust weakly supervised learning method, which selects the threshold combinations and processing flows instead of labor-intensive annotation work to construct the ground truth of the dataset, and design a deep neural network, FURNet, based on UNet++ and ResNeXt. The model obtained from training achieves high-quality vascular segmentation and captures multi-scene vascular features on both constructed and unknown datasets with good generalization. Furthermore, we intravital verified the availability of this method on a tumor before and after embolization treatment. This work provides a new approach for realizing LSCI vascular segmentation and also makes a new application-level advance in the field of artificial intelligence-assisted disease diagnosis.

In this work, we present a method to estimate the planar mass distribution of a rigid object through robotic interactions and force/torque feedback. This is a challenging problem because of the complexity of modeling physical dynamics and the action dependencies across the model parameters. We propose a sequential estimation strategy combined with a set of robot action selection rules based on the analytical formulation of a discrete-time dynamics model. To evaluate the performance of our approach, we also manufactured re-configurable block objects that allow us to modify the object mass distribution while having access to the ground truth values. We compare our approach against multiple baselines and show that it can estimate the mass distribution with around 10% error, while the baselines have errors ranging from 18% to 68%.

We study a semantic SLAM problem where a robot is tasked with autonomous weeding under the corn canopy. The goal is to detect corn stalks and localize them in a global coordinate frame. This is a challenging scenario for existing algorithms because there is very little space between the camera and the plants, and the camera motion is primarily restricted to be along the row. To overcome these challenges, we present a multi-camera system where a side camera (facing the plants) is used for detection, whereas front and back cameras are used for motion estimation. Next, we show how semantic features in the environment (corn stalks, ground, and crop planes) can be used to develop a robust semantic SLAM solution and present results from field trials performed throughout the growing season across various cornfields.

Learning object manipulation is a critical skill for robots to interact with their environment. Even though there has been significant progress in robotic manipulation of rigid objects, interacting with non-rigid objects remains challenging for robots. In this work, we introduce velcro peeling as a new application for robotic manipulation of non-rigid objects in complex environments. We present a method of learning force-based manipulation from noisy and incomplete sensor inputs in partially observable environments by modeling long term dependencies between measurements with a multi-step deep recurrent network. We present experiments on a real robot to show the necessity of modeling these long term dependencies and validate our approach in simulation and robot experiments. Our results show that using tactile input enables the robot to overcome geometric uncertainties present in the environment with high fidelity in ∼ 90% of all cases, outperforming the baselines by a large margin.