In this article, a novel simulation-to-real (sim2real) multimodal learning framework is proposed for adaptive dexterous grasping and grasp status prediction. A two-stage approach is built upon the Isaac Gym and several proposed pluggable modules, which can effectively simulate dexterous grasps with multimodal sensing data, including RGB-D images of grasping scenarios, joint angles, 3-D tactile forces of soft fingertips, etc. Over 500K multimodal synthetic grasping scenarios are collected for neural network training. An adaptive dexterous grasping neural network (ADG-Net) is trained to learn dexterous grasp principles and predict grasp parameters, employing an attention mechanism and a graph convolutional neural network module to fuse multimodal information. The proposed adaptive dexterous grasping method can detect feasible grasp parameters from an RGB-D image of a grasp scene and then optimize grasp parameters based on multimodal sensing data when the dexterous hand touches a target object. Various experiments in both simulation and physical grasps indicate that our ADG-Net grasping method outperforms state-of-the-art grasping methods, achieving an average success rate of 92% for grasping isolated unseen objects and 83% for stacked objects. Code and video demos are available at https://github.com/huikul/adgnet.

Robotic rigid contact-rich manipulation in an unstructured dynamic environment requires an effective resolution for smart manufacturing. As the most common use case for the intelligence industry, a lot of studies based on reinforcement learning (RL) algorithms have been conducted to improve the performances of single peg-in-hole assembly. However, existing RL methods are difficult to apply to multiple peg-in-hole issues due to more complicated geometric and physical constraints. In addition, previously limited solutions for multiple peg-in-hole assembly are hard to transfer into real industrial scenarios flexibly. To effectively address these issues, this work designs a novel and more challenging multiple peg-in-hole assembly setup by using the advantage of the Industrial Metaverse. We propose a detailed solution scheme to solve this task. Specifically, multiple modalities, including vision, proprioception, and force/torque, are learned as compact representations to account for the complexity and uncertainties and improve the sample efficiency. Furthermore, RL is used in the simulation to train the policy, and the learned policy is transferred to the real world without extra exploration. Domain randomization and impedance control are embedded into the policy to narrow the gap between simulation and reality. Evaluation results demonstrate the effectiveness of the proposed solution, showcasing successful multiple peg-in-hole assembly and generalization across different object shapes in real-world scenarios.

Markerless vision-based teleoperation that leverages innovations in computer vision offers the advantages of allowing natural and noninvasive finger motions for multifingered robot hands. However, current pose estimation methods still face inaccuracy issues due to the self-occlusion of the fingers. Herein, we develop a novel vision-based hand-arm teleoperation system that captures the human hands from the best viewpoint and at a suitable distance. This teleoperation system consists of an end-to-end hand pose regression network and a controlled active vision system. The end-to-end pose regression network (Transteleop), combined with an auxiliary reconstruction loss function, captures the human hand through a low-cost depth camera and predicts joint commands of the robot based on the image-to-image translation method. To obtain the optimal observation of the human hand, an active vision system is implemented by a robot arm at the local site that ensures the high accuracy of the proposed neural network. Human arm motions are simultaneously mapped to the slave robot arm under relative control. Quantitative network evaluation and a variety of complex manipulation tasks, for example, tower building, pouring, and multitable cup stacking, demonstrate the practicality and stability of the proposed teleoperation system.

Grasping an object when it is in an ungraspable pose is a challenging task, such as books or other large flat objects placed horizontally on a table. Inspired by human manipulation, we address this problem by pushing the object to the edge of the table and then grasping it from the hanging part. In this paper, we develop a model-free Deep Reinforcement Learning framework to synergize pushing and grasping actions. We first pre-train a Variational Autoencoder to extract high-dimensional features of input scenario images. One Proximal Policy Optimization algorithm with the common reward and sharing layers of Actor-Critic is employed to learn both pushing and grasping actions with high data efficiency. Experiments show that our one network policy can converge 2.5 times faster than the policy using two parallel networks. Moreover, the experiments on unseen objects show that our policy can generalize to the challenging case of objects with curved surfaces and off-center irregularly shaped objects. Lastly, our policy can be transferred to a real robot without fine-tuning by using CycleGAN for domain adaption and outperforms the push-to-wall baseline.

Currently, task-oriented grasp detection approaches are mostly based on pixel-level affordance detection and semantic segmentation. These pixel-level approaches heavily rely on the accuracy of a 2D affordance mask, and the generated grasp candidates are restricted to a small workspace. To mitigate these limitations, we firstly construct a novel affordance-based grasp dataset and propose a 6-DoF task-oriented grasp detection framework, which takes the observed object point cloud as input and predicts diverse 6-DoF grasp poses for different tasks. Specifically, our implicit estimation network and visual affordance network in this framework could directly predict coarse grasp candidates, and corresponding 3D affordance heatmap for each potential task, respectively. Furthermore, the grasping scores from coarse grasps are combined with heatmap values to generate more accurate and finer candidates. Our proposed framework shows significant improvements compared to baselines for existing and novel objects on our simulation dataset. Although our framework is trained based on the simulated objects and environment, the final generated grasp candidates can be accurately and stably executed in the real robot experiments when the object is randomly placed on a support surface.

Planar pushing remains a challenging research topic, where building the dynamic model of the interaction is the core issue. Even an accurate analytical dynamic model is inherently unstable because physics parameters such as inertia and friction can only be approximated. Data-driven models usually rely on large amounts of training data, but data collection is time consuming when working with real robots.In this paper, we collect all training data in a physics simulator and build an LSTM-based model to fit the pushing dynamics. Domain Randomization is applied to capture the pushing trajectories of a generalized class of objects. When executed on the real robot, the trained recursive model adapts to the tracked object's real dynamics within a few steps. We propose the algorithm Recurrent Model Predictive Path Integral (RMPPI) as a variation of the original MPPI approach, employing state-dependent recurrent models. As a comparison, we also train a Deep Deterministic Policy Gradient (DDPG) network as a model-free baseline, which is also used as the action generator in the data collection phase. During policy training, Hindsight Experience Replay is used to improve exploration efficiency. Pushing experiments on our UR5 platform demonstrate the model's adaptability and the effectiveness of the proposed framework.

In this paper, we present a multimodal mobile teleoperation system that consists of a novel vision-based hand pose regression network (Transteleop) and an IMU (inertial measurement units)-based arm tracking method. Transteleop observes the human hand through a low-cost depth camera and generates not only joint angles but also depth images of paired robot hand poses through an image-to-image translation process. A keypoint-based reconstruction loss explores the resemblance in appearance and anatomy between human and robotic hands and enriches the local features of reconstructed images. A wearable camera holder enables simultaneous hand-arm control and facilitates the mobility of the whole teleoperation system. Network evaluation results on a test dataset and a variety of complex manipulation tasks that go beyond simple pick-and-place operations show the efficiency and stability of our multimodal teleoperation system.

Robust and accurate estimation of liquid height lies as an essential part of pouring tasks for service robots. However, vision-based methods often fail in occluded conditions while audio-based methods cannot work well in a noisy environment. We instead propose a multimodal pouring network (MP-Net) that is able to robustly predict liquid height by conditioning on both audition and haptics input. MP-Net is trained on a self-collected multimodal pouring dataset. This dataset contains 300 robot pouring recordings with audio and force/torque measurements for three types of target containers. We also augment the audio data by inserting robot noise. We evaluated MP-Net on our collected dataset and a wide variety of robot experiments. Both network training results and robot experiments demonstrate that MP-Net is robust against noise and changes to the task and environment. Moreover, we further combine the predicted height and force data to estimate the shape of the target container.

In this paper, we present TeachNet, a novel neural network architecture for intuitive and markerless vision-based teleoperation of dexterous robotic hands. Robot joint angles are directly generated from depth images of the human hand that produce visually similar robot hand poses in an end-to-end fashion. The special structure of TeachNet, combined with a consistency loss function, handles the differences in appearance and anatomy between human and robotic hands. A synchronized human-robot training set is generated from an existing dataset of labeled depth images of the human hand and simulated depth images of a robotic hand. The final training set includes 400K pairwise depth images and joint angles of a Shadow C6 robotic hand. The network evaluation results verify the superiority of TeachNet, especially regarding the high-precision condition. Imitation experiments and grasp tasks teleoperated by novice users demonstrate that TeachNet is more reliable and faster than the state-of-the-art vision-based teleoperation method.

In this paper, we propose an end-to-end grasp evaluation model to address the challenging problem of localizing robot grasp configurations directly from the point cloud. Compared to recent grasp evaluation metrics that are based on handcrafted depth features and a convolutional neural network (CNN), our proposed PointNetGPD is lightweight and can directly process the 3D point cloud that locates within the gripper for grasp evaluation. Taking the raw point cloud as input, our proposed grasp evaluation network can capture the complex geometric structure of the contact area between the gripper and the object even if the point cloud is very sparse. To further improve our proposed model, we generate a large-scale grasp dataset with 350k real point cloud and grasps with the YCB object set for training. The performance of the proposed model is quantitatively measured both in simulation and on robotic hardware. Experiments on object grasping and clutter removal show that our proposed model generalizes well to novel objects and outperforms state-of-the-art methods. Code and video are available at https://lianghongzhuo.github.io/PointNetGPD.

In this paper, we focus on the challenging perception problem in robotic pouring. Most of the existing approaches either leverage visual or haptic information. However, these techniques may suffer from poor generalization performances on opaque containers or concerning measuring precision. To tackle these drawbacks, we propose to make use of audio vibration sensing and design a deep neural network PouringNet to predict the liquid height from the audio fragment during the robotic pouring task. PouringNet is trained on our collected real-world pouring dataset with multimodal sensing data, which contains more than 3000 recordings of audio, force feedback, video and trajectory data of the human hand that performs the pouring task. Each record represents a complete pouring procedure. We conduct several evaluations on PouringNet with our dataset and robotic hardware. The results demonstrate that our PouringNet generalizes well across different liquid containers, positions of the audio receiver, initial liquid heights and types of liquid, and facilitates a more robust and accurate audio-based perception for robotic pouring.