In recent years, Chinese Long March(LM) launchers have experienced several launch failures, most of which occurred in their propulsion systems, and this paper studies Autonomous Mission Reconstruction(AMRC) technology...In recent years, Chinese Long March(LM) launchers have experienced several launch failures, most of which occurred in their propulsion systems, and this paper studies Autonomous Mission Reconstruction(AMRC) technology to alleviate losses due to these failures. The status of the techniques related to AMRC, including trajectory and mission planning, guidance methods,and fault tolerant technologies, are reviewed, and their features are compared, which reflect the challenges faced by AMRC technology. After a brief introduction about the failure modes of engines that can occur during flight, and the fundamentals of trajectory planning and joint optimization of the target orbit and flight path, an AMRC algorithm is proposed for geostationary transfer orbit launch missions. The algorithm evaluates the residual performance onboard, and plans new objectives and corresponding flight path by iterative guidance mode or segmented state triggered optimization methods in real-time. Three failure scenarios that have occurred during previous LM missions are simulated to check the robustness of the algorithm: imminent explosion risk of the boosters’ engines, thrust drop during the first stage of flight, and being unable to start the engine during the second stage. The payloads would fall from space according to the current design under these conditions, but they were saved with the AMRC algorithm in the simulations, which allowed the rocket to get into the target orbit as intended or the payloads were deployed in other orbits without crashing. Although spaceflight can be very unforgiving, the AMRC algorithm has the potential to avoid the total loss of a launch mission when faced with these kinds of typical failures.展开更多
Machine-to-Machine (M2M) collaboration opens new opportunities where systems can collaborate without any human intervention and solve engineering problems efficiently and effectively. M2M is widely used for various ap...Machine-to-Machine (M2M) collaboration opens new opportunities where systems can collaborate without any human intervention and solve engineering problems efficiently and effectively. M2M is widely used for various application areas. Through this reported project authors developed a M2M system where a drone and two ground vehicles collaborate through a base station to implement a system that can be utilized for an indoor search and rescue operation. The model training for drone flight paths achieves almost 100% accuracy. It was also observed that the accuracy of the model increased with more training samples. Both the drone flight path and ground vehicle navigation are controlled from the base station. Machine learning is utilized for modelling of drone’s flight path as well as for ground vehicle navigation through obstacles. The developed system was implemented on a field trial within a corridor of a building, and it was demonstrated successfully.展开更多
机巡作业是当前电力巡检的主要发展方向,但与直升机、无人机以及变电站机器人相比,我国输电线路机器人巡检尚未达到实用化水平。为此,对输电线路机器人实用化巡检关键技术开展了研究,建立了机器人典型作业模式,研发了穿越式、跨越式两...机巡作业是当前电力巡检的主要发展方向,但与直升机、无人机以及变电站机器人相比,我国输电线路机器人巡检尚未达到实用化水平。为此,对输电线路机器人实用化巡检关键技术开展了研究,建立了机器人典型作业模式,研发了穿越式、跨越式两类巡检机器人,提出了机器人行走路径改造方法,首次设计了机器人自动上下线装置,并完成了机器人全自主巡检系统的研制。机器人通过了多种复杂自然环境和电磁环境工况的试验考核,以及户外真型线路试验段的功能测试,在500 k V带电运行线路开展示范应用,对线路设备同时进行可见光和红外检测。巡检中暴露了巡检系统存在的问题并进行分析解决,提出了机器人异常情况下的紧急救援措施并成功开展带电救援作业。机器人单次巡检里程达到10 km以上,巡检应用取得良好效果,机器人巡检系统达到一定的实用化水平。展开更多
This paper proposes a new approach for detecting human survivors in destructed environments using an autonomous robot. The proposed system uses a passive infrared sensor to detect the existence of living humans and a ...This paper proposes a new approach for detecting human survivors in destructed environments using an autonomous robot. The proposed system uses a passive infrared sensor to detect the existence of living humans and a low-cost camera to acquire snapshots of the scene. The images are fed into a feed-forward neural network, trained to detect the existence of a human body or part of it within an obstructed environment. This approach requires a relatively small number of images to be acquired and processed during the rescue operation, which considerably reduces the cost of image processing, data transmission, and power consumption. The results of the conducted experiments demonstrated that this system has the potential to achieve high performance in detecting living humans in obstructed environments relatively quickly and cost-effectively. The detection accuracy ranged between 79% and 91% depending on a number of factors such as the body position, the light intensity, and the relative color matching between the body and the surrounding environment.展开更多
基金co-supported by International Academy of Astronautics (IAA) study group SG 3.32the National Natural Science Foundation of China (No. 61773341)
文摘In recent years, Chinese Long March(LM) launchers have experienced several launch failures, most of which occurred in their propulsion systems, and this paper studies Autonomous Mission Reconstruction(AMRC) technology to alleviate losses due to these failures. The status of the techniques related to AMRC, including trajectory and mission planning, guidance methods,and fault tolerant technologies, are reviewed, and their features are compared, which reflect the challenges faced by AMRC technology. After a brief introduction about the failure modes of engines that can occur during flight, and the fundamentals of trajectory planning and joint optimization of the target orbit and flight path, an AMRC algorithm is proposed for geostationary transfer orbit launch missions. The algorithm evaluates the residual performance onboard, and plans new objectives and corresponding flight path by iterative guidance mode or segmented state triggered optimization methods in real-time. Three failure scenarios that have occurred during previous LM missions are simulated to check the robustness of the algorithm: imminent explosion risk of the boosters’ engines, thrust drop during the first stage of flight, and being unable to start the engine during the second stage. The payloads would fall from space according to the current design under these conditions, but they were saved with the AMRC algorithm in the simulations, which allowed the rocket to get into the target orbit as intended or the payloads were deployed in other orbits without crashing. Although spaceflight can be very unforgiving, the AMRC algorithm has the potential to avoid the total loss of a launch mission when faced with these kinds of typical failures.
文摘Machine-to-Machine (M2M) collaboration opens new opportunities where systems can collaborate without any human intervention and solve engineering problems efficiently and effectively. M2M is widely used for various application areas. Through this reported project authors developed a M2M system where a drone and two ground vehicles collaborate through a base station to implement a system that can be utilized for an indoor search and rescue operation. The model training for drone flight paths achieves almost 100% accuracy. It was also observed that the accuracy of the model increased with more training samples. Both the drone flight path and ground vehicle navigation are controlled from the base station. Machine learning is utilized for modelling of drone’s flight path as well as for ground vehicle navigation through obstacles. The developed system was implemented on a field trial within a corridor of a building, and it was demonstrated successfully.
文摘机巡作业是当前电力巡检的主要发展方向,但与直升机、无人机以及变电站机器人相比,我国输电线路机器人巡检尚未达到实用化水平。为此,对输电线路机器人实用化巡检关键技术开展了研究,建立了机器人典型作业模式,研发了穿越式、跨越式两类巡检机器人,提出了机器人行走路径改造方法,首次设计了机器人自动上下线装置,并完成了机器人全自主巡检系统的研制。机器人通过了多种复杂自然环境和电磁环境工况的试验考核,以及户外真型线路试验段的功能测试,在500 k V带电运行线路开展示范应用,对线路设备同时进行可见光和红外检测。巡检中暴露了巡检系统存在的问题并进行分析解决,提出了机器人异常情况下的紧急救援措施并成功开展带电救援作业。机器人单次巡检里程达到10 km以上,巡检应用取得良好效果,机器人巡检系统达到一定的实用化水平。
文摘This paper proposes a new approach for detecting human survivors in destructed environments using an autonomous robot. The proposed system uses a passive infrared sensor to detect the existence of living humans and a low-cost camera to acquire snapshots of the scene. The images are fed into a feed-forward neural network, trained to detect the existence of a human body or part of it within an obstructed environment. This approach requires a relatively small number of images to be acquired and processed during the rescue operation, which considerably reduces the cost of image processing, data transmission, and power consumption. The results of the conducted experiments demonstrated that this system has the potential to achieve high performance in detecting living humans in obstructed environments relatively quickly and cost-effectively. The detection accuracy ranged between 79% and 91% depending on a number of factors such as the body position, the light intensity, and the relative color matching between the body and the surrounding environment.
