Search

The construction industry has long been plagued by low productivity and high injury and fatality rates. Robots have been envisioned to automate the construction process, thereby substantially improving construction productivity and safety. Despite the enormous potential, teaching robots to perform complex construction tasks is challenging. We present a generalizable framework to harness human teleoperation data to train construction robots to perform repetitive construction tasks. First, we develop a teleoperation method and interface to control robots on construction sites, serving as an intermediate solution toward full automation. Teleoperation data from human operators, along with context information from the job site, can be collected for robot learning. Second, we propose a new method for extracting keyframes from human operation data to reduce noise and redundancy in the training data, thereby improving robot learning efficacy. We propose a hierarchical imitation learning method that incorporates the keyframes to train the robot to generate appropriate trajectories for construction tasks. Third, we model the robot's visual observations of the working space in a compact latent space to improve learning performance and reduce computational load. To validate the proposed framework, we conduct experiments teaching a robot to generate appropriate trajectories for excavation tasks from human operators' teleoperations. The results suggest that the proposed method outperforms state-of-the-art approaches, demonstrating its significant potential for application. [ABSTRACT FROM AUTHOR]

Peripheral nerve injury exacerbates progression of muscle heterotopic ossification (HO) and induces changes in expression of local cytokines in muscle tissue. The objective of the present study was to assess the impact of peripheral nerve injury on muscle HO development and the mechanism of cytokine modulation. A mouse model of gastrocnemius muscle HO was established and the sciatic nerve cut to simulate peripheral nerve injury. To evaluate the underlying factors contributing to the exacerbation of muscle HO resulting from denervation, fresh muscle tissue was collected and micro-computed tomography, histochemical staining, RNA-sequencing, reverse transcription-quantitative PCR, Western blot, muscle tissue chip array were performed to analyze the molecular mechanisms. Sciatic nerve injury exacerbated HO in the gastrocnemius muscle of mice. Moreover the osteogenic differentiation of nerve-injured muscle tissue-derived fibro-adipogenic progenitors (FAPs) increased in vitro. The expression of neuregulin 3 (NRG3) was demonstrated to be increased after nerve injury by muscle tissue chip array. Subsequent transcriptome sequencing analysis of muscle tissue revealed an enrichment of the PI3K/Akt pathway following nerve injury and an inhibitor of the PI3K/Akt pathway reduced the osteogenic differentiation of FAPs. Mechanistically, in vitro, peripheral nerve injury increased secretion of NRG3, which, following binding to ErbB4 on the cell surface of FAPs, promoted expression of osteogenesis-associated genes via the PI3K/Akt signaling pathway, thus contributing to osteogenic differentiation of FAPs. In vivo, inhibition of the PI3K/Akt pathway effectively protected against muscle HO induced by peripheral nerve injury in mice. The present study demonstrated that the regulatory roles of NRG3 and the PI3K/Akt pathway in peripheral nerve injury exacerbated muscle HO and highlights a potential therapeutic intervention for treatment of peripheral nerve injury-induced muscle HO. [ABSTRACT FROM AUTHOR]

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.robot.2006.06.003 Byline: Weihua Sheng (a), Qingyan Yang (b), Jindong Tan (c), Ning Xi (d) Abstract: This paper proposes a reliable and efficient multi-robot coordination algorithm to accomplish an area exploration task given that the communication range of each robot is limited. This algorithm is based on a distributed bidding model to coordinate the movement of multiple robots. Two measures are developed to accommodate the limited-range communications. First, the distances between robots are considered in the bidding algorithm so that the robots tend to stay close to each other. Second, a map synchronization mechanism, based on a novel sequence number-based map representation and an effective robot map update tracking, is proposed to reduce the exchanged data volume when robot subnetworks merge. Simulation results show the effectiveness of the use of nearness measure, as well as the map synchronization mechanism. By handling the limited communication range we can make the coordination algorithms more realistic in multi-robot applications. Author Affiliation: (a) School of ECE, Oklahoma State University, Stillwater, OK 74078, United States (b) Systems Division, Iteris Inc., Madison Heights, MI 48071, United States (c) ECE. Department, Michigan Technological University, Houghton, MI 49931, United States (d) ECE. Department, Michigan State University, East Lansing, MI 48824, United States Article History: Received 6 December 2004; Revised 16 June 2006; Accepted 16 June 2006