Papers by Alireza Bab-hadiashar
IEEE Transactions on Vehicular Technology, Mar 1, 2008
The elimination of a clamp-force sensor from brake-by-wire system designs is strongly demanded du... more The elimination of a clamp-force sensor from brake-by-wire system designs is strongly demanded due to implementation difficulties and cost issues. In this paper, a new method is presented to estimate the clamp force based on other sensory information. This estimator fuses the outputs of two models to optimize the root-mean-square error (RMSE) of estimation. Experimental results show that the estimator can accurately track the true clamp force for high-speed cases as demanded by the antilock braking system controls. A training strategy has been used to ensure that the estimator can successfully adapt to parameter variations associated with wear. This paper is concluded with a discussion on the reliability of the developed clamp-force estimator.
IEEE Transactions on Industrial Electronics, Mar 1, 2015
Brushless motors are increasingly used in different designs of in-wheel electric vehicles (EVs). ... more Brushless motors are increasingly used in different designs of in-wheel electric vehicles (EVs). In this paper, a sensorless antilock braking system (ABS) for brushless-motor in-wheel EVs is proposed. The proposed solution omits the need for installation of separate conventional ABS sensors at each corner of the vehicle. This paper also shows, both theoretically and experimentally, that the general form of a conventional ABS sensor output voltage is identical to a brushless dc (BLDC)-motor back electromotive force. The proposed sensorless system can reduce the costs of manufacturing and maintenance of the vehicle and significantly improves the performance of the ABS by accurate wheel speed estimation and road identification using wavelet signal processing methods. The sensorless system was extensively tested using actual ABS hardware. Those experiments showed that the accuracy of the proposed sensorless wheel speed estimation for BLDC propulsion was higher than that of commercial ABS sensors. In addition, sensorless ABS for brushless propulsion was compared with that of brushed dc motor, and the results showed that the brushless sensorless ABS achieved better accuracy, robustness, and reliability compared with the sensorless ABS for brushed dc motor. Index Terms-Antilock braking system (ABS), brushless motor, continuous wavelet transform (CWT), discrete wavelet transform (DWT), electric vehicle (EV), in-wheel technology, regenerative braking, sensorless ABS.
Signal Processing, Jun 1, 2020
This is a PDF file of an article that has undergone enhancements after acceptance, such as the ad... more This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.
Springer eBooks, Jul 29, 2013
ABSTRACT A new approach to solve the sensor control problem is proposed, formulated based on mult... more ABSTRACT A new approach to solve the sensor control problem is proposed, formulated based on multi-object Bayes filtering in the partially observable Markov decision process (POMDP) context, where the multi-object states are assumed to be random finite sets with multi-Bernoulli distributions. We introduce a novel cost function that is reliable in real-time environment. In each filtering iteration, after predicting the multi-Bernoulli parameters, estimates for the number and states of the targets are extracted. For each admissible control command, Monte-Carlo samples of measurements corresponding to the estimated target states are generated. Then, for each measurement sample, the CB-MeMBer update is performed and the average cost function is computed. The best command is the one incurring the minimum cost. The simulation results involve a challenging case of detecting and tracking up to 5 manoeuvring targets using a controllable sensor, and show that our method outperforms competing methods both in terms of tracking accuracy (measured in using OSPA metric) and in terms of computational cost.
arXiv (Cornell University), Apr 20, 2016
This paper presents a track-before-detect labeled multi-Bernoulli filter tailored for industrial ... more This paper presents a track-before-detect labeled multi-Bernoulli filter tailored for industrial mobile platform safety applications. We derive two application specific separable likelihood functions that capture the geometric shape and colour information of the human targets who are wearing a high visible vest. These likelihoods are then used in a labeled multi-Bernoulli filter with a novel two step Bayesian update. Preliminary simulation results show that the proposed solution can successfully track human workers wearing a luminous yellow colour vest in an industrial environment.
A new approach to optic flow calculation, based on a highly robust statistical technique, is pres... more A new approach to optic flow calculation, based on a highly robust statistical technique, is presented. In this algorithm, the optic flow problem is first formulated as a standard least squares problem. Then, its associated closest point problem is introduced and the transformation which takes this problem to a standard regression problem is provided. The Least Median of Squares technique is used to solve the resulting regression problem. Some experimental results for both synthetic and real image sequences are also presented.
Robotics and Autonomous Systems, Nov 1, 2003
This paper describes the implementation and evaluation of four reactive robot chemotaxis algorith... more This paper describes the implementation and evaluation of four reactive robot chemotaxis algorithms. If they are applicable, reactive algorithms can provide fast, simple and cost-effective solutions for robot control applications. As part of this evaluation a robot was developed that has sufficient resources to enable it to implement each of the chemotaxis algorithms. The robot has bilateral chemical sensors, an airflow sensor and tactile whiskers to detect obstacles. Chemotaxis algorithms observed in the bacterium E. coli, the silkworm moth Bombyx mori, and the dung beetle Geotrupes stercorarius were tested as well as a gradient-based algorithm. There are many potential applications for chemical sensing robots particularly in situations where animals such as sniffer dogs are currently used. These applications include locating victims of avalanches or earthquakes and detecting landmines. Robotic systems offer a number of benefits compared to the use of animals, including rapid deployment, low maintenance costs and operation for extended periods. Details of the algorithms are given together with typical results obtained using the algorithms in both simulated and practical experiments. The design of the chemical sensing robot and the relative merits and demerits of the different chemotaxis algorithms are also discussed.
The International Journal of Advanced Manufacturing Technology, Dec 5, 2022
arXiv (Cornell University), Mar 25, 2015
This paper presents a sensor-control method for choosing the best next state of the sensor(s), th... more This paper presents a sensor-control method for choosing the best next state of the sensor(s), that provide(s) accurate estimation results in a multi-target tracking application. The proposed solution is formulated for a multi-Bernoulli filter and works via minimization of a new estimation error-based cost function. Simulation results demonstrate that the proposed method can outperform the state-of-the-art methods in terms of computation time and robustness to clutter while delivering similar accuracy.
This thesis was scanned from the print manuscript for digital preservation and is copyright the a... more This thesis was scanned from the print manuscript for digital preservation and is copyright the author. Researchers can access this thesis by asking their local university, institution or public library to make a request on their behalf. Monash staff and postgraduate students can use the link in the Reference field.
Real-time 3D mapping has many applications and has recently received a large interest due to avai... more Real-time 3D mapping has many applications and has recently received a large interest due to availability of consumer depth cameras at low prices. In this paper, we present a 3D registration and mapping method that heuristically switches between photometric and geometric features, therefore allowing it to accurately register scenes that may lack either visual or geometric information. We propose a novel informative sampling based geometric 3D feature extraction technique in which the points carrying the most useful geometric information are used for registration. This increases the computational speed significantly while preserving the accuracy of the registration when compared to using the dense point cloud for registration. After extracting the features from sequential frames, they are assigned with feature descriptors and matched with their correspondences from the previous frame. The matches are then refined and a rigid transformation between the frames is calculated using a highly robust estimator. A global pose for the camera and associated 3D position of the points are computed by concatenating the estimated relative transformations and a 3D map is constructed. We evaluate our method on publicly available RGB-D benchmark datasets [1] and compare it to the state of the art algorithms.
In many cases, the multi-target tracking system is essential for realizing the current state of a... more In many cases, the multi-target tracking system is essential for realizing the current state of an environment. The standard multi-target tracking algorithms assume that each target state evolves independently and regardless of other targets' states. However, in a real scenario this assumption does not hold in that the motion of any target is dependent on other targets. This paper proposes a new mathematical solution for multi-target tracking system with interacting targets. In the proposed method the prediction operation of the labeled multi-Bernoulli filter is extended to incorporate all possible interactions between targets. The results show that in scenarios where the assumption of a standard motion model is violated, the proposed method achieves higher accuracy for the state estimation of the targets. Also, it shows better performance for estimating the identity of the targets.
Proceedings of the ... ISARC, May 24, 2019
Statistical reports point to the fact that civil infrastructure projects remain hazardous working... more Statistical reports point to the fact that civil infrastructure projects remain hazardous working environments. Despite the implementation of various safety procedures, the frequency and cost of work-related injuries are significant. Improvements in sensor technologies, wireless communication and processing power of computers as well as advancements in machine learning and computer vision are now enabling datadriven systems as effective safety barriers for accident prevention. In recent years, many researchers have studied various methods of leveraging technology to improve safety in civil infrastructure projects. However, previous investigations have not produced a thorough analysis of the practicality of those approaches. While considerable progress has been made in developing methods to improve construction safety, few studies have focused on implementation of data-driven real-time accident prevention systems to effectively minimize risk in the event where other safety measures have failed or been absent. Motivated to facilitate the development of such method, this paper carries out thorough analysis of the field and its trends, identifies research gaps, provides a discussion of recent advancements, and highlights future research directions to help researchers gain an upto-date overview of the state-of-the-art and navigate through this domain efficiently.
Deep learning methods have recently made a significant breakthrough in many classification proble... more Deep learning methods have recently made a significant breakthrough in many classification problems. Deep convolutional networks realize the possibility of building large-scale data representations with multiple processing layers. A scattering transform is an effective and relatively recent deep convolutional network that builds large-scale informative representations by cascading linear and nonlinear operators in multiple layers. However, experimental results show that scattering coefficients have a significantly low energy at higher layers and subsequently have little impact on classification results. In this paper, we propose a multi-wavelet fusion-based architecture to improve the error of classification by using scattering transforms. The method effectively increases the energy of scattering coefficients at higher levels via a further step of applying a linear operator followed by a nonlinear operator. Our experimental results showed that the proposed method achieves better classification results compared to the original scattering transform, and thus can be used as an effective method for texture classification problems.
International Journal of Vehicle Autonomous Systems, 2015
An electronic differential for high-performance electric vehicles with independent driving motors... more An electronic differential for high-performance electric vehicles with independent driving motors is proposed in this paper. This electronic differential endows the electric vehicle with a close-to-zero vehicle side-slip angle. When vehicle side-slip vanishes, the heading direction of the vehicle coincides with the velocity direction of the mass centre. In addition to the side-slip angle, the yaw rate is driven towards an optimal value with the proposed electronic differential on-board. The improvements in vehicle side-slip and yaw rate responses are of great significance to the handling performance of high-performance vehicles. In this paper, the mathematical relationships between the vehicle dynamic states and the independent motor torques are revealed, based on which the proposed electronic differential controller is designed. Simulation results manifest that in various challenging steering scenarios, the proposed control method outperforms two common electronic differential control schemes in terms of vehicle side-slip and yaw rate responses.
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 1, 2022
State-of-the-art stereo matching networks trained only on synthetic data often fail to generalize... more State-of-the-art stereo matching networks trained only on synthetic data often fail to generalize to more challenging real data domains. In this paper, we attempt to unfold an important factor that hinders the networks from generalizing across domains: through the lens of shortcut learning. We demonstrate that the learning of feature representations in stereo matching networks is heavily influenced by synthetic data artefacts (shortcut attributes). To mitigate this issue, we propose an Information-Theoretic Shortcut Avoidance (ITSA) approach to automatically restrict shortcutrelated information from being encoded into the feature representations. As a result, our proposed method learns robust and shortcut-invariant features by minimizing the sensitivity of latent features to input variations. To avoid the prohibitive computational cost of direct input sensitivity optimization, we propose an effective yet feasible algorithm to achieve robustness. We show that using this method, stateof-the-art stereo matching networks that are trained purely on synthetic data can effectively generalize to challenging and previously unseen real data scenarios. Importantly, the proposed method enhances the robustness of the synthetic trained networks to the point that they outperform their finetuned counterparts (on real data) for challenging out-ofdomain stereo datasets.
In the past decade, there have been great advancements in the application of computer vision to U... more In the past decade, there have been great advancements in the application of computer vision to UAV's and associated aerial visual surveillance. For example, [6] demonstrated how a high precision ego-motion estimate of a camera can be incorporated to achieve video annotations and insertion to reference imagery. An algorithm for estimating the approach angle of an Unmanned Aerial Vehicle (UAV) is presented. The Algorithm involves extracting the horizon and the focus-of-expansion (from opticflow employing robust statistics). Experimental results are presented to validate this approach. Many UAV implementations incorporate a Global Satellite Positioning System (GPS) or Inertial Navigation System (INS) for aircraft position and displacement measurements. The feasibility of using vision alone to extract aircraft position is demonstrated in [3]. By matching the real-time video feed with a set of reference IRS images or a Digital Evaluation Map (DEM), absolute position was estimated.
This paper presents a novel solution to the occlusion handling problem in pedestrian tracking usi... more This paper presents a novel solution to the occlusion handling problem in pedestrian tracking using labeled random finite set theory. The occlusion handling module uses motion and color cues of tracked targets to recover target labels after occlusion. An effective algorithm is also proposed for false alarm detection and removal which is designed based on tracked targets features such as, overlap ratio, size similarity and the time of track initialization of the tracked targets. We implement our solution using sequential Monte Carlo method, and compare it with state-of-the-art visual tracking methods. The results show that the proposed algorithm perform favorably in terms of various standard performance metrics.
Uploads
Papers by Alireza Bab-hadiashar