Lessons learned deploying space planning systems

This article describes a number of lessons learned in deploying automated planning and scheduling systems for space applications at the Jet Propulsion Laboratory. Specifically, we describe issues relating to: how plan representation can affect plan quality; how to acquire, validate and maintain planning knowledge bases; and how planning and execution can be integrated. These issues are described in the context of several fielded systems in the areas of science data analysis, ground station automation, and spacecraft autonomy.     

Goal distance estimation for automated planning using neural networks and support vector machines

Many of today’s most successful planners perform a forward heuristic search. The accuracy of the heuristic estimates and the cost of their computation determine the performance of the planner. Thanks to the efforts of researchers in the area of heuristic search planning, modern algorithms are able to generate high-quality estimates. In this paper we propose to learn heuristic functions using artificial neural networks and support vector machines. This approach can be used to learn standalone heuristic functions but also to improve standard planning heuristics. One of the most famous and successful variants for heuristic search planning is used by the Fast-Forward (FF) planner. We analyze the performance of standalone learned heuristics based on nature-inspired machine learning techniques and employ a comparison to the standard FF heuristic and other heuristic learning approaches. In the conducted experiments artificial neural networks and support vector machines were able to produce standalone heuristics of superior accuracy. Also, the resulting heuristics are computationally much more performant than related ones.     

Process sequencing and process clustering in process planning using state space search

Process sequencing, as a very important part of process planning, has been the subject of many research reports in the area of process planning, but is usually treated as a feature-sequencing problem. This paper presents a novel algorithm for process sequencing, which considers the feature precedence network, different process candidates, and machine and tool constraints. The algorithm consists of two parts: process clustering and process sequencing. For clustering we used a notion of the same resource usage for different features, while for sequencing we applied the best-first search method algorithm to generate an optimal process sequence. The algorithm has been applied on several examples with realistic complexities, and it showed satisfactory results.     

Path planning for collision avoidance using a glid-like space

Many remote-control robots are being developed. And they are hoped to work in extreme environmental conditions such as lifesaving or rescue. These robots required complicate movement and precise works. Almost remote controller are often discussed for the position control on the end effector under camera images. However, it is difficult to control a robot arm using limited information in the monitor, as it is difficult for personnel to perform sensitive work while controlling a robot with the limited view information. This results in high stress for the driver and can cause operational mistakes. Therefore, it is important to use robot easily under a limited view. In this report, we propose a simplification method for a beginner user. We present a computed support system to control the robot arm easily with increased sensitivity, combined with grid-like space and a joystick.     

Secure and advanced unpacking using computer emulation

The purpose of this article is firstly to present a secure unpacker which is specifically designed for a security analyst when studying viruses but also any anti-virus scanner. Such a tool is in fact required when assessing security requirements of an anti-virus scanner through a black box approach. During testing of anti-virus software, a security analyst needs to build virus populations required for several penetration tests. Virus unpacking is a first mandatory step before gaining the ability to apply obfuscation transformation or any information extraction algorithm on a viral set. A secure unpacker is also useful when checking security robustness against reverse engineering of any packed or protected security product. Several static and dynamic analysis tools already implement unpacking algorithms, but these often require human intervention and are not well designed to automatically unpack such a dangerous program as a virus. A new algorithm for automatically unpacking encrypted viruses is presented in this paper. Forensics techniques to reconstruct an unpacked executable and advanced heuristics are also presented in order to decrypt more sophisticated self-protected Malwares. We present several detection techniques which are specifically designed to deceive virtual machine monitors and discuss the security of our tool against these low-level viral attacks. Our secure unpacker figures among a set of several tools. We then present in this paper a proof-of-concept human analysis framework which implements most standard components of an anti-virus scanner (real-time scanner, emulator engine) and in addition proposes a reliable system for automatically gaining information about a virus and its interaction with the OS executive (stealth native API hooking), but focuses on human decision as a detection process without the same resource limitation constraint as product oriented anti-virus scanners. This framework is used as a basis/reference for the comparative analysis of security aspects of anti-virus scanners and deals with the robustness of their driver stack and the efficiency of their de-obfuscation and unpacking algorithms. This paper is the extended version presented at the AVAR 2006 Conference [39]. Sébastien Josse is an I.T. consultant at Silicomp-AQL Security Evaluation Lab and also a Ph.D. student EDX Polytechnique Doctoral School within the ESAT Virology and Cryptology Lab in Rennes email: sebastien.josse@esat.terre.defense.gouv.fr.     

Optimum motion planning in joint space for robots using genetic algorithms

The optimum motion planning in joint space (OMPJS) for robots, which generally consists of two subproblems, optimum path planning and optimum trajectory planning, was considered as a whole in the paper. A new method for optimum motion planning problem based on an improved genetic algorithm is proposed, which is more general, flexible and effective. This approach incorporates kinematics constraints, dynamics constraints, and control constraints of robotic manipulator. The simulation results for a two and a three degrees of freedom robots are presented and discussed. The simulations are based on genetic algorithm class library WGAClass 1.0 developed by us with Borland C++ 3.1.     

Model-based space planning for temporary structures using simulation-based multi-objective programming

Construction trades need to share temporary structures to increase the output of direct work while controlling the labor input of indirect work. The purpose of this research is to develop a framework to determine the optimal location of temporary structures in a computerized practical manner for piping construction projects. Based on the spatial relationship between work envelope and scaffolding placement requirements, this paper presents the optimization model in two phases: the simulation-based optimization model and a multi-attribute utility (MAU) based alternative selection model. A multi-objective optimization model is established to improve scaffolding availability among multiple activities while maximizing piping crew productivity. The multi-attribute utility model is employed to handle the uncertainty of the assessment weights on the attributes to illustrate the preference of decision makers among different scaffolding placement alternatives obtained from the first phase. The approach was validated in a piping module, which provided superintendents and space planners with an effective decision-making tool among possible scaffolding alternatives in piping construction. The proposed optimization technique is an alternative methodology for solving the productivity-tasks-scaffolding trade-off problem, which further revolutionizes the spatial coordination process of workspace management and temporary structure planning.     

Architectural space planning using evolutionary computing approaches: a review

This paper presents various applications of evolutionary computing approach for architectural space planning problem. As such the problem of architectural space planning is NP-complete. Finding an optimal solution within a reasonable amount of time for these problems is impossible. However for architectural space planning problem we may not be even looking for an optimal but some feasible solution based on varied parameters. Many different computing approaches for space planning like procedural algorithms, heuristic search based methods, genetic algorithms, fuzzy logic, and artificial neural networks etc. have been developed and are being employed. In recent years evolutionary computation approaches have been applied to a wide variety of applications as it has the advantage of giving reasonably acceptable solution in a reasonable amount of time. There are also hybrid systems such as neural network and fuzzy logic which incorporates the features of evolutionary computing paradigm. The present paper aims to compare the various aspects and merits/demerits of each of these methods developed so far. Sixteen papers have been reviewed and compared on various parameters such as input features, output produced, set of constraints, scope of space coverage-single floor, multi-floor and urban spaces. Recent publications emphasized on energy aspect as well. The paper will help the better understanding of the Evolutionary computing perspective of solving architectural space planning problem. The findings of this paper provide useful insight into current developments and are beneficial for those who look for automating architectural space planning task within given design constraints.     

Optimal space planning in practice

The Computer Aided Design Group's Space Planning System, a general facility for optimal spatial arrangement of activities in buildings, is described. Case studies of application in practice are presented and discussed, and the influence of practical experience with real spatial arrangement problems on the design of the software is described.     

University space planning and space-type profiles

Universities planning the provision of space for their teaching requirements need to do so in a fashion that reduces capital and maintenance costs whilst still providing a high-quality level of service. Space plans should aim to provide sufficient capacity without incurring excessive costs due to over-capacity. A simple measure used to estimate over-provision is utilisation. Essentially, the utilisation is the fraction of seats that are used in practice, or the ratio of demand to supply. However, studies usually find that utilisation is low, often only 20–40%, and this is suggestive of significant over-capacity.     

Multi-objective path planning in discrete space

Finding a path for a robot which is near to natural looking paths is a challenging problem in motion planning. This paper suggests two single and multi-objective optimization models focusing on length and clearance of the path in discrete space. Considering the complexity of the models and potency of evolutionary algorithms we apply a genetic algorithm with NSGA-II framework for solving the problems addressed in the models. The proposed algorithm uses an innovative family of path refiner operators, in addition to the standard genetic operators. The new operators intensify explorative power of the algorithm in finding Pareto-optimal fronts in the complicated path planning problems such as narrow passages and clutter spaces. Finally, we compare efficiency of the refiner operators and the algorithm with PSO and A* algorithms in several path planning problems.     

Discriminative human action recognition in the learned hierarchical manifold space

In this paper, we propose a hierarchical discriminative approach for human action recognition. It consists of feature extraction with mutual motion pattern analysis and discriminative action modeling in the hierarchical manifold space. Hierarchical Gaussian Process Latent Variable Model (HGPLVM) is employed to learn the hierarchical manifold space in which motion patterns are extracted. A cascade CRF is also presented to estimate the motion patterns in the corresponding manifold subspace, and the trained SVM classifier predicts the action label for the current observation. Using motion capture data, we test our method and evaluate how body parts make effect on human action recognition. The results on our test set of synthetic images are also presented to demonstrate the robustness.     

Goal assignment and trajectory planning for large teams of interchangeable robots

This paper presents Goal Assignment and Planning: a computationally tractable, complete algorithm for generating dynamically feasible trajectories for \(N\) interchangeable (identical) robots navigating through known cluttered environments to \(M\) goal states. This is achieved by assigning goal states to robots to minimize the maximum cost over all robot trajectories. The computational complexity of this algorithm is shown to be polynomial in the number of robots in contrast to the expected exponential complexity associated with planning in the joint state space. This algorithm can be used to plan trajectories for dozens of robots, each in a potentially high dimensional state space. A series of planar case studies are presented and finally, experimental trials are conducted with a team of six quadrotor robots navigating in a constrained three-dimensional environment.     

基于改进遗传算法的狭窄空间路径规划

针对室内或地下等狭窄而复杂环境下的移动机器人全局路径规划,提出了一种基于Dijkstra算法的改进遗传算法路径规划策略,以解决传统遗传算法在狭窄环境下难以有效初始化的问题。首先借助Dijkstra算法得出基准路径,然后以此基准路径为基础,通过改进的编码方式与搜索空间进行初始种群的编码,最后通过遗传算法获得最优路径。提出了全局通行度和路径安全度的概念,用来评估当机器人不可视为质点时的环境状态与路径优劣。仿真实验结果表明,与传统遗传算法和人工势场法相比,本方法在保证路径距离较短的情况下,能使路径安全度提高50%以上,或者将时间复杂度降低一半以上,表明了所提方法的实用性和有效性。     

智能空间中的服务机器人路径规划

为了加深服务机器人对环境的理解,实现安全高效的智能空间导航,建立了一种信息更为丰富的环境模型——危险度地图;并针对智能空间环境部分未知的特点,设计了分层的路径规划方法.静态规划层根据已知环境信息,采用改进的粒子群优化算法规划初始最优路径,动态规划层利用基于动态危险度地图的改进A＊算法进行避障.该方法克服了常规算法只追求路径最短的缺点,增加了对路径危险度的评价,规划出的路径既安全又较短;且该方法实现简单,实时性好.仿真结果验证了该方案的可行性.     

Design space optimization using design space adjustment and refinement

To deal with large-scale problems that often occur in industry, the authors propose design space optimization with design space adjustment and refinement. In topology optimization, a design space is specified by the number of design variables, and their layout or configuration. The proposed procedure has two efficient algorithms for adjusting and refining design space. First, the design space can be adjusted in terms of design space expansion and reduction. This capability is evolutionary because the design domain expands or reduces wherever necessary. Second, the design space can be refined uniformly or selectively wherever and whenever necessary, ensuring a target resolution with fewer elements, especially for selective refinement. Accordingly, the proposed procedure can handle large-scale problems by solving a sequence of smaller problems. Two examples show the efficiency of the proposed approach.     

Regional land planning based on BPNN and space mining technology

Neural Computing and Applications - The rationality of regional land planning needs to be evaluated through intelligent technology and continuously optimized. At present, most land planning is...     

基于嵌入式系统的机器人关节空间轨迹规划

针对工业机器人运行过程经常出现的因速度或加速度不连续从而导致抖动等问题,提出了一种基于B样条曲线的轨迹规划算法,该算法使用三次B样条曲线来对六自由度机器人的关节空间进行插值,并根据实时性的要求运用一种控制点衔接插补算法进行分段插补,最终应用于基于ARM9的嵌入式系统中。实验证明:该算法不仅计算量小、处理时间短,而且能保证速度曲线的连续平滑,减少了机械抖动。     

Fostering collaborative learning in Second Life: Metaphors and affordances

In this paper we examine the transferability of the Jigsaw and Fishbowl collaborative learning techniques to the Second Life platform. Our aim is to assess the applicability of Second Life for collaborative learning by developing virtual tools and metaphors and exploiting the representational richness of this novel medium. In order to enhance the existing metaphors and affordances of SL, our research team implemented educational spaces, avatar clothing, and tools for non-verbal communication and visualisation. By implementing a blended learning evaluation approach we attempted to answer three research questions focusing on student collaboration, avatar representation and learning space awareness. We can conclude that SL can supplement and/or augment face to face interactions, improving upon previous approaches in distance collaboration and communication. Furthermore, although our team augmented SL’s ability to support collaborative learning, avatar representation does not seem to scale well. Finally, the majority of the implemented affordances and metaphors seem to have enhanced collaboration and learning space awareness.     

Leveraging the affordances of Youtube: The role of pedagogical knowledge and mental models of technology functions for lesson planning with technology

Web-based digital video tools enable learners to access video sources in constructive ways. To leverage these affordances teachers need to integrate their knowledge of a technology with their professional knowledge about teaching. We suggest that this is a cognitive process, which is strongly connected to a teacher’s mental model of the tool’s affordances. First we elaborate the theoretical integration of the notion of mental models and the Technological Pedagogical Content Knowledge (TPCK) framework. Then we report on a study where we investigated pedagogical knowledge in a sample of German pre-service teachers as a predictor for their mental models of YouTube and how these affect lesson plans for instructional use of this technology. We describe the active mental models of YouTube and present quantitative analyses suggesting mental models as mediators for the influence of pedagogical knowledge on participants’ lesson planning. Results are discussed with regard to theoretical and research implications.