Virtual Reality (VR) robot embodiment is a popular method for teleoperation and generating data to train AI control systems. A potential flaw with this approach is an incongruence in human-robot haptics. Without tactile feedback, teleoperators depend on visual cues, leading to suboptimal performance (slow movement, faulty grasps, excessive contact force). This problem is exacerbated during robot hand teleoperation. Worse, many haptic hand wearables are cable-driven and only produce unidirectional resistive force, thus failing to cover the gamut of 3D finger interactions. In this paper, a critical gap in teleoperated human-robot hand haptics is addressed by transforming an inexpensive (~500 USD) 3D-printed robotic hand into a wearable exoskeleton—the "Hand-in-Hand" (HiH) system—which provides fingertip 3D force feedback. Methods for force control, null-space optimization, and human finger pose estimation are presented and experimentally validated. Each finger of the device can produce a maximum of 1N of force feedback in any 3D direction. HiH finger tracking is compared to an industry-grade device (MANUS Metagloves, 5000 USD) and realizes an average inferred joint position Normalized Root Mean Square Error of 33.46%. Lastly, the HiH is demonstrated within a VR robot embodiment experiment with force feedback. Operator hand-manipulation performance improved when using force feedback, emphasizing the HiH’s potential for teleoperated robot control and data collection.

This paper presents Team Avatar-Hubo’s Avatar system designed for telepresence, along with our strategy to fulfill the testing task requirements in the ANA Avatar XPRIZE Finals. Our system is built upon the foundation of DRC-Hubo and incorporates a VR Motion Tracker system, bi-directional audio feedback, visual feedback, haptic sensing, and navigation. During the ANA Avatar XPRIZE Finals evaluation, our proposed Avatar system achieved the 11th Place Award among a pool of 17 Finalists. We provide comprehensive insights into our Avatar System, including its Hardware-Software Architecture, capabilities in Auditory-Vision, manipulation, Texture perception, locomotion, and Interface. Furthermore, we extensively discuss the key lessons we learned during our participation in the competition.

This paper presents a study that evaluates the effects on the walking pattern of a full-sized humanoid robot as it pushes different carts. Furthermore, it discuss a modified Zero Moment Point (ZMP) pattern based on a capture point method, and a friction compensation method for the arms. Humanoid researchers have demonstrated that robots can perform a wide range of tasks including handling tools, climbing ladders, and patrolling rough terrain. However, when it comes to handling objects while walking, humanoids are relatively limited; it becomes more apparent when humanoids have to push a cart. Many challenges become evident under such circumstances; for example, the walking pattern will be severely affected by the external force opposed by the cart. Therefore, an appropriate walking pattern dynamic model and arm compliance are needed to mitigate external forces. This becomes crucial in order to ensure the robot's self-balance and minimize external disturbances.

Automation in construction continues to be a topic of interest for many in industry and academia. However, the dynamic environments presented in construction sites prove these tasks to be difficult to automate reliably. This paper proposes a novel method of teleoperation for multiple heterogeneous robots within a construction environment. The system is achieved by creating a virtual reality interface that allows an operator to control multiple robots both synchronously and asynchronously. Feedback is provided from an array of RGBD cameras, force sensors, and precise odometry data. The DRC-Hubo and Spot robot platforms are used for implementation and experimentation. Experiments include useful tasks for construction including item manipulation and item delivery of tools and components. Results demonstrate the feasibility of implementing the system in a construction environment, including trajectory comparisons, task learning curves, and successful multi-robot collaboration.