Large-scale, diverse datasets are essential for training robust learning-based robotic manipulation models; however, their acquisition typically requires controlled environments and specialized hardware in research laboratories. This paper presents VRobotix, a virtual reality (VR)-based framework that enables cost-effective and scalable robotic dataset generation through immersive human-in-the-loop control within a physics-accurate robot simulation. By leveraging off-the-shelf VR headsets (e.g., Oculus Quest 3), VRobotix eliminates the need for physical robots while supporting a URDF-compatible, physics-based simulator that accommodates adaptable robotic platforms and egocentric control interfaces, including handheld controllers and body posture tracking. Benefiting from the physics-based simulation, a unique contribution of VRobotix is the replay module, which can regenerate synchronized multi-modal dataset (kinematic states, RGB-D streams) with multiple dataset formats based on the replayable trajectory, supporting various robotic applications. Additionally, an imitation learning module is developed to train control policies using the data collected by VRobotix. Experiments on three initial tasks—pushing, grasping, and stacking—demonstrate a high data collection success rate, averaging 92.0%. Furthermore, policies trained on just 50 trials achieve a 100% task success rate. VRobotix reduces infrastructure costs while generating ROS-compatible datasets, democratizing scalable robotic data acquisition.

Pouring fluids is a routine task for humans but challenging for high-DoF robots, particularly given fluid simulation’s computational demands while training policies. In this paper, we propose DexPour, a novel reinforcement learning method with hierarchical rewards and Approximated Proxy Abstraction (APA) method. APA efficiently approximates liquid behavior using a small set of spheres, reducing computational overhead. Meanwhile, our hierarchical reward framework breaks down the intricate pouring process into four distinct stages—approach, grasp, transport, and pour—providing fine-grained feedback and fostering stable policy learning. Extensive experiments demonstrate that DexPour achieves a 92% fluid transfer efficiency with a 70% cup fill and a 99% efficiency at 30% fill, highlighting its robust performance across varying liquid volumes. Ablation studies highlight the contribution of each component, confirming the necessity of detailed stage-wise guidance for complex dexterous manipulation. In addition, we compare DexPour with a full fluid simulation baseline, showing comparable pouring efficiency while reducing training time by 81.6%, demonstrating DexPour’s efficiency and practical viability for fluid manipulation tasks.

Tactile sensors can significantly enhance the perception of humanoid robotics systems by providing contact information that facilitates human-like interactions. However, existing commercial tactile sensors focus on improving the resolution and sensitivity of single-modal detection with high-cost components and densely integrated design, incurring complex manufacturing processes and unaffordable prices. In this work, we present Bio-Skin, a cost-effective multi-modal tactile sensor that utilizes single-axis Hall-Effect sensors for planar normal force measurement and bar-shape piezo resistors for 2D shear force measurement. A thermistor coupling with a heating wire is integrated into a silicone body to achieve temperature sensation and thermostatic function analogous to human skin. We also present a cross-reference framework to validate the two modalities of the force sensing signal, improving the sensing fidelity in a complex electromagnetic environment. Bio-Skin has a multi-layer design, and each layer is manufactured sequentially and subsequently integrated, thereby offering a fast production pathway. After calibration, Bio-Skin demonstrates performance metrics—including signal-to-range ratio, sampling rate, and measurement range—comparable to current commercial products, with one-tenth of the cost. The sensor’s real-world performance is evaluated using an Allegro hand in object grasping tasks, while its temperature regulation functionality was assessed in a material detection task.

Dexterous telemanipulation critically relies on the continuous and stable tracking of the human operator’s commands to ensure robust operation. Vison-based tracking methods are widely used but have low stability due to anomalies such as occlusions, inadequate lighting, and loss of sight. Traditional filtering, regression, and interpolation methods are commonly used to compensate for explicit information such as angles and positions. These approaches are restricted to low-dimensional data and often result in information loss compared to the original high-dimensional image and video data. Recent advances in diffusion-based approaches, which can operate on high-dimensional data, have achieved remarkable success in video reconstruction and generation. However, these methods have not been fully explored in continuous control tasks in robotics. This work introduces the Diffusion-Enhanced Telemanipulation (DET) framework, which incorporates the Frame-Difference Detection (FDD) technique to identify and segment anomalies in video streams. These anomalous clips are replaced after reconstruction using diffusion models, ensuring robust telemanipulation performance under challenging visual conditions. We validated this approach in various anomaly scenarios and compared it with the baseline methods. Experiments show that DET achieves an average RMSE reduction of 17.2% compared to the cubic spline and 51.1% compared to FFT-based interpolation for different occlusion durations.

Simulation to Real-World Transfer allows affordable and fast training of learning-based robots for manipulation tasks using Deep Reinforcement Learning methods. Currently, Asymmetric Actor-Critic approaches are used for Sim2Real to reduce the rich idealized features in simulation to the accessible ones in the real world. However, the feature reduction from the simulation to the real world is conducted through an empirically defined one-step curtail. Small feature reduction does not sufficiently remove the actor’s features, which may still cause difficulty setting up the physical system, while large feature reduction may cause difficulty and inefficiency in training. To address this issue, we proposed Curriculum-based Sensing Reduction to enable the actor to start with the same rich feature space as the critic and then get rid of the hard-to-extract features step-by-step for higher training performance and better adaptation for real-world feature space. The reduced features are replaced with random signals from a Deep Random Generator to remove the dependency between the output and the removed features and avoid creating new dependencies. The methods are evaluated on the Allegro robot hand in a real-world in-hand manipulation task. The results show that our methods have faster training and higher task performance than baselines and can solve real-world tasks when selected tactile features are reduced.

Dexterous telemanipulation is crucial in advancing human-robot systems, especially in tasks requiring precise and safe manipulation. However, it faces significant challenges due to the physical differences between human and robotic hands, the dynamic interaction with objects, and the indirect control and perception of the remote environment. Current approaches predominantly focus on mapping the human hand onto robotic counterparts to replicate motions, which exhibits a critical oversight: it often neglects the physical interaction with objects and relegates the interaction burden to the human to adapt and make laborious adjustments in response to the indirect and counter-intuitive observation of the remote environment. This work develops an End-Effects-Oriented Learning-based Dexterous Telemanipulation (EFOLD) framework to address telemanipulation tasks. EFOLD models telemanipulation as a Markov Game, introducing multiple end-effect features to interpret the human operator’s commands during interaction with objects. These features are used by a Deep Reinforcement Learning policy to control the robot and reproduce such end effects. EFOLD was evaluated with real human subjects and two end-effect extraction methods for controlling a virtual Shadow Robot Hand in telemanipulation tasks. EFOLD achieved real-time control capability with low command following latency (delay<0.11s) and highly accurate tracking (MSE<0.084 rad).

In-hand manipulation is challenging for a multi-finger robotic hand due to its high degrees of freedom and complex interaction with the object. To enable in-hand manipulation, existing deep reinforcement learning-based approaches mainly focus on training a single robot-structure-specific policy through the centralized learning mechanism, lacking adaptability to changes like robot malfunction. To solve this limitation, this work treats each finger as an individual agent and trains multiple agents to control their assigned fingers to complete the in-hand manipulation task cooperatively. We propose the Multi-Agent Global-Observation Critic and Local-Observation Actor (MAGCLA) method, where the critic can observe all agents' actions globally, and the actor only locally observes its neighbors' actions. Besides, conventional individual experience replay may cause unstable cooperation due to the asynchronous performance increment of each agent, which is critical for in-hand manipulation tasks. To solve this issue, we propose the Synchronized Hindsight Experience Replay (SHER) method to synchronize and efficiently reuse the replayed experience across all agents. The methods are evaluated in two in-hand manipulation tasks on the Shadow dexterous hand. The results show that SHER helps MAGCLA achieve comparable learning efficiency to a single policy, and the MAGCLA approach is more generalizable in different tasks. The trained policies have higher adaptability in the robot malfunction test compared to the baseline multi-agent and single-agent approaches.

Applying Deep Reinforcement Learning (DRL) to Human-Robot Cooperation (HRC) in dynamic control problems is promising yet challenging as the robot needs to learn the dynamics of the controlled system and dynamics of the human partner. In existing research, the robot powered by DRL adopts coupled observation of the environment and the human partner to learn both dynamics simultaneously. However, such a learning strategy is limited in terms of learning efficiency and team performance. This work proposes a novel task decomposition method with a hierarchical reward mechanism that enables the robot to learn the hierarchical dynamic control task separately from learning the human partner’s behavior. The method is validated with a hierarchical control task in a simulated environment with human subject experiments. Our method also provides insight into the design of the learning strategy for HRC. The results show that the robot should learn the task first to achieve higher team performance and learn the human first to achieve higher learning efficiency.