1、A comprehensive survey of augmented reality assembly research,Abstract provide a concise overview of the technical features,characteristics and broad range of applications of ARbased assembly systems published between 1990 and 2015.Introduction 1.traditional computer-aided assembly technology：requir

2、 to identify constraint information between the mating parts；difficult to foresee the impact of individual mating specifications on other aspects of the assembly process；lacks direct interaction between users andthe components. 2.VR assembly system：lacking of realistic experience，decreasing the fide

3、lity and credibility ；not easy to fully and accurately model the real-time and actual working environments. 3.AR assembly system：does not need the entire real world to be modeled；enhances the interaction between the systems and the users，manipulate the objects naturally.,Six functional modules of AR

4、 assembly system,Three main categories AR assembly system,120 articles，39.47%,116 articles，38.16%,68 articles，22.37%,AR multi-media and interactive instructions Disadvantage： focus solely on providing step-based instructions，overlooking users need of timely guidance in assembly operations； could not

5、 keep track of theassembly status in real-time and recognize errors and completion states ； when assisting complex assembly processes，time-consuming authoring procedures, integration with enterprise data； the interaction scheme may disturb or interrupt users on-going assembly task. Target: detecting

6、 and recognizing the users actions in order to provide an industrial robust hands free interaction. examine the appropriateness of AR guidance for more complex, multi-step assembly tasks.,Context-awareness and authoring AR assembly system keeps track of the status of users in real-time, automaticall

7、y recognizing manual errors and completion at each assembly step and displaying multimedia instructions corresponding to the recognized states. AR assembly authoring systems have been enabled to cope with manual assembly operations efficiently; Disadvantage： time-consuming to build ad hoc systems. n

8、eed manual input. Target: to be more task-adaptive, suite for a wide range of different tasks. consider the implementation issues of sensors. become smart enough to understand a users intent and generate timely context-aware guidance during assembly operations without manual input.,Evaluation of AR

9、assembly guidance 1.Effectiveness evaluation: concerns the capability of the system to produce a desired result for a certain task or activity. 2.Usability evaluation: involves investigating the ease of use and learnability of the AR assembly system based on needs analysis, user interviews and exper

10、t evaluations. Disadvantage： different factors that influence the effectiveness and usability of an AR assembly system are still obscure. such as various interaction methods. designed only for a specific ad hoc assembly task. Trend： evaluating novel AR interfaces, especially how these interfaces can

11、 improve human resource capabilities and the attendant human factors.,AR assembly training Research in this area has largely involved procedural tasks where a user follows visual or other multi-modal cues to perform a series of steps, with the focus on maximizing the users efficiency while using the

12、 AR system Disadvantage： provide minimal feedback when the users make a mistake, which is not conducive to learning. Target: the adaptivity of various methods and difficulty levels of assembly operations would be expected to be integrated to the AR assembly training system. handle current trends of

13、agile product development and manufacturing.,AR assembly process simulation and planning many of the current AR assembly simulation systems seem to be limited to the interaction between virtual objects. ignore an important issue of incorporating real objects into the AR environment to provide the co

14、re benefits of AR.such as haptic feedback, natural interaction and better manipulation intuition. Hand-based HCI has become a popular research topic in AR assembly simulation. Disadvantage： the user need to undertake specific simple actions to implement the interaction with the AR environment. the a

15、ction lack intuitiveness. only a limited types of gestures have been used and the gestures are designed by researchers for optimal recognition rather than for naturalness. the mappings between gestures and commands to the computer are often arbitrary.,assembly design and planning The implementation

16、of assembly design and planning in the AR environment is promising and a growing number of researchers have studied this area. Disadvantage： accuracy issue, intuitiveness and dependency on CADsoftware. Target: to construct an integrated AR assembly platform to model the interaction between mating co

17、mponents accurately. to propose an information management method to extracts information from CAD system, stores and reasons the assembly relations independently.,Marker-based tracking The use of markers is very common in AR assembly because it increases the robustness and improves the computation e

18、fficiency due to the stable and fast detection of markers. Disadvantage： suffer from marker occlusion. industrial components are too small to attach markers. Sensor-based tracking The tracking principle is based on different types of sensors. Vision based tracking relies on computer vision technique

19、s.,Marker-less tracking be deemed to be a desirable successor of markers recently. Disadvantage: the trade-offs between the tracking accuracy and computation cost need to be considered carefully.,Collaborative AR interface a technology aimming at assembly designers, planners as well as operators can

20、 participate together to facilitate communication between them during assembly process. Ranatunga et al. presented a method that allowed an expert to use multi-touch gestures to translate, rotate and annotate an object on a video feed to facilitate remote guidance in the collaboration with other use

21、rs. Target: there is not rigorous user studies. Formal user studies need to be conducted in future collaborative AR research.,3D workspace scene capture,a stereo camera has the ability to capture 3D images for 3D reconstruction,but the accuracy of the camera is not linear. it cannt calculate the dis

22、tance of every pixel. even the state-of-the-art dense 3D reconstruction techniques usually suffer from insufficient accuracy, resulting in visual artifacts, such as loss of detailed shapes and rough boundaries.,Conclusions (i)Advanced computer vision technology to capture the 3D workspace scene with depth informa