Weria Khaksar's research while affiliated with Norwegian University of Life Sciences (NMBU) and other places

Publications (24)

Article
Full-text available
Sampling-based motion planning is a powerful tool in solving the motion planning problem for a variety of different robotic platforms. As its application domains grow, more complicated planning problems arise that challenge the functionality of these planners. One of the main challenges in the implementation of a sampling-based planner is its weak...
Chapter
Despite the proven advantages of probabilistic motion planning algorithms in solving complex navigation problems, their performance is restricted by the selected nodes in the configuration space. Furthermore, the choice of selecting the neighbor nodes and expanding the graph structure is limited by a set of deterministic measures such as Euclidean...
Article
Full-text available
Despite the proven advantages of sampling-based motion planning algorithms, their inability to handle online navigation tasks and providing low-cost solutions make them less efficient in practice. In this paper, a novel sampling-based algorithm is proposed which is able to plan in an unknown environment and provides solutions with lower cost in ter...
Article
Full-text available
In robotics, resolution of several difficult issues requires process intelligence. In many applications, the environment of a robot changes with time in a manner that has not been foreseen by its designer. Additionally, information on the environment is commonly inaccurate and incomplete, which is attributed to the restricted sensory activity of se...
Article
Full-text available
Elderly care at home is a matter of great concern if the elderly live alone, since unforeseen circumstances might occur that affect their well-being. Technologies that assist the elderly in independent living are essential for enhancing care in a cost-effective and reliable manner. Elderly care applications often demand real-time observation of the...
Article
Full-text available
A depth camera-based novel method is proposed here for efficient facial expression recognition. For each pixel in a depth image, eight local directional strengths are obtained and ranked. Once the rank of all pixels are obtained, eight histograms are developed for the eight surrounding directions. The histograms are then concatenated to represent f...
Article
Full-text available
This study focuses on existing drawbacks and inefficiencies of the available path planning approaches within unknown dynamic environments. The drawbacks are the inability to plan under uncertain dynamic environments, non-optimality, failure in crowded complex situations, and difficulty in predicting the velocity vector of obstacles. This study aims...
Article
Accurate Wind speed forecasting has a vital role in efficient utilization of wind farms. Wind forecasting could be performed for long or short time horizons. Given the volatile nature of wind and its dependent on many geographical parameters, it is difficult for traditional methods to provide a reliable forecast of wind speed time series. In this s...
Article
Full-text available
Accurate wind speed forecasting has a vital role in efficient utilization of wind farms. Wind forecasting could be performed for long or short time horizons. Given the volatile nature of wind and its dependent on many geographical parameters, it is difficult for traditional methods to provide a reliable forecast of wind speed time series. In this s...
Article
This review study presents the utilization of different evolutionary algorithms (EAs) for plate-fin heat exchanger (PFHE) design optimization in the last decade. The traditional trialand- error design process of CHEs can be replaced by a more flexible and easy-to-implement evolutionary approach. EAs do need any information of derivatives and theref...

Citations

... They identified 13 variables that all affect user acceptance of social robots. For some people it might be necessary to reach a higher comfort level, e.g., elderly people might prefer a larger distance (Khaksar et al., 2021). Alternatively, in specific contexts, it might be necessary to make a trade-off between robot efficiency and human comfort, and there developers might choose to take a lower perceived comfort criterion. ...
... However, statistical approaches mentioned in [24] does not suffer from this problem. However, many papers designed new methods to solve these problems of thermal images and used combination of CNN and Recurrent Neural Network (RNN) for HAR [30,31]. ...
... Hrabar (2008) proposed a combination of the PRM algorithm and D* Lite for path planning, where a stereo camera embedded in the robot is used to detect obstacles and dynamically update the path in unknown configuration space. Khaksar et al. (2019) also proposed a combination of the D* Lite algorithm and random roadmap algorithm for path planning in complex terrain. In general, there is not much work to deal with the issue of generating effective sampling points in narrow corridors, though the path planning with sparse obstacles has been extensively discussed (Qureshi and Ayaz, 2016). ...
... Hence, the purpose of the navigation control method based on imitation learning is to learn the best mapping between the output motion action of the navigation controller and the input LiDAR sensing data and the relative target position. For example, Khaksar et al. [15] proposed a mapless neuro-fuzzy motion planner learned from a virtual experience model, which generates enough training data to train the adaptive neuro-fuzzy inference system. Pfeiffer et al. [16] proposed a data-driven motion planning approach based on a featurebased maximum entropy model, which is trained to predict the joint navigation behavior of heterogeneous groups of agents based on the demonstration of human-human interactions. ...
... Selama ini penelitian masih terbatas pada navigasi robot mobile dengan metode tertentu seperti pemanfaatan logika fuzzy pada algoritma navigasi [1], navigasi untuk pemetaan jalan yang dilalui robot [2], adaptasi robot untuk menentukan rute pada peta yang diberikan peta lingkungan [3], algoritma sampling cepat pada sistem navigasi robot mobile pada medan yang tak pasti [4]. Fungsi robot mobile autonomous dapat bergerak bebas mencapai tujuan dengan mengatasi rintangan menggunakan algoritma heuristic [5] dan menghindari tabrakan menggunakan beberapa tipe algoritma logika fuzzy [6]. ...
... Initial dip detection can decrease the time required for the generation of BCI commands [32]. The work on prediction algorithms is also one of the major focus in the field of initial dip and can open several new avenues in future for quick generation of command [33][34][35]. For the existence of an initial dip, interested readers can refer to Hong and Zafar [36]. ...
... Hill-Climbing algorithm was selected again to solve the proposed optimization problem, figure 6 shows the length reduction for the problem used as an example in this section, although the results depends on the geometry of the map selected. As explained before, not only the proposed algorithm but the original PRM method require a know map or a partially constructed map to plan a trajectory, there are different methods to build maps using sensors on a mobile platform, such as the SLAM algorithm [14], in this case the map is created using ultrasonic and Lidar sensors, the map is presented as an occupancy grid, as described in section II. Figure 7 shows the maps used for comparison in this work, they are ordered by degree of difficulty due to the configuration of its obstacles, some of these maps were taken from the literature [15], [16]. Each map have a resolution of 100 x 300 pixels. ...
... In image alignment, feature point detection can be used to obtain feature points of two images, and then the alignment can be completed by matching these feature points. Common feature point detection methods such as: Harris Corner Detection, and Scale Invariant Feature Transformation (SIFT) [28][29][30]. As well, this system adopts SIFT method to carry on the detection, the flow chart is shown in Figure 5. ...
... Despite the benefits of these tools, such solutions are often abandoned due to quality issues (7). In particular, sampling clinically relevant parameters with a high sensitivity and testretest reliability by non-research-grade end-consumer devices, such as activity trackers (8), apps, and smart-home installations (9), is still challenging. Continuous reliability is essential for ensuring adequate quality and forms the basis for personalizing interventions and preventive measures, which, in turn, influence acceptance and usability (7). ...
... Due to this fact, it has been widely used in many application systems (Rida et al. (2019)) like video surveillance, forensics, and criminal activities investigation processes. However, the performance of gait recognition systems (Uddin et al. (2017); Chi, Wang, and Meng (2017)) highly depends on the appearance of people like their clothing, things that they are carrying, and environmental variations. For resolving this problem, different types of machine learning (Bhargavas et al. (2017)) and deep learning models are used in the conventional works, which mainly intend to obtain outstanding performance outcomes in gait recognition (El-Alfy et al. increased recognition, ensured robustness, and accuracy. ...