Pedram Agand

Title: “Sequential Modeling of Complex Marine Navigation: Case Study on a Passenger Vessel (Student Abstract)”

Author:Y. Fan, P. Agand, M. Chen, E. J. Park, A. Kennedy, C. Bae

Abstract: The maritime industry’s continuous commitment to sustainability has led to a dedicated exploration of methods to reduce vessel fuel consumption. This paper undertakes this challenge through a machine learning approach, leveraging a real-world dataset spanning two years of a ferry in west coast Canada. Our focus centers on the creation of a time series forecasting model given the dynamic and static states, actions, and disturbances. This model is designed to predict dynamic states based on the actions provided, subsequently serving as an evaluative tool to assess the proficiency of the ferry’s operation under the captain’s guidance. Additionally, it lays the foundation for future optimization algorithms, providing valuable feedback on decision-making processes.
To facilitate future studies, our code is available at Github.

Title: “Fuel Consumption Prediction for a Passenger Ferry using Machine Learning and In-service Data: A Comparative Study”

Author: P. Agand, A. Kennedy, T. Harris, C. Bae, M. Chen, and E. J. Park

Abstract: As the importance of eco-friendly transportation increases, providing an efficient approach for marine vessel operation is essential. Methods for status monitoring with consideration to the weather condition and forecasting with the use of in-service data from ships requires accurate and complete models for predicting the energy efficiency of a ship. The models need to effectively process all the operational data in real-time. This paper presents models that can predict fuel consumption using in-service data collected from a passenger ship. Statistical and domain-knowledge methods were used to select the proper input variables for the models. These methods prevent over-fitting, missing data, and multicollinearity while providing practical applicability. Prediction models that were investigated include multiple linear regression (MLR), decision tree approach (DT), an artificial neural network (ANN), and ensemble methods. The best predictive performance was from a model developed using the XGboost technique which is a boosting ensemble approach. \rvv{Our code is available on GitHub for future research. 

Title: “Deep Reinforcement Learning-based Intelligent Traffic Signal Controls with Optimized CO2 emissions”

Author: P.  Agand, A. Iskrov, and M. Chen

Abstract: Nowadays, transportation networks face the challenge of sub-optimal control policies that can have adverse effects on human health, the environment, and contribute to traffic congestion. Increased levels of air pollution and extended commute times caused by traffic bottlenecks make intersection traffic signal controllers a crucial component of modern transportation infrastructure. Despite several adaptive traffic signal controllers in literature, limited research has been conducted on their comparative performance. Furthermore, despite carbon dioxide (CO2) emissions’ significance as a global issue, the literature has paid limited attention to this area. In this report, we propose EcoLight, a reward shaping scheme for reinforcement learning algorithms that not only reduces CO2 emissions but also achieves competitive results in metrics such as travel time. We compare the performance of tabular Q-Learning, DQN, SARSA, and A2C algorithms using metrics such as travel time, CO2 emissions, waiting time, and stopped time. Our evaluation considers multiple scenarios that encompass a range of road users (trucks, buses, cars) with varying pollution levels.

Title: “LeTFuser: Light-weight End-to-end Transformer-Based Sensor Fusion for Autonomous Driving with Multi-Task Learning”

Author: P. Agand,  M. Mahdavian, M. Savva, and M. Chen.

Abstract: In end-to-end autonomous driving, the utilization of existing sensor fusion techniques for imitation learning proves inadequate in challenging situations that involve numerous dynamic agents. To address this issue, we introduce LeTFuser, a transformer-based algorithm for fusing multiple RGB-D camera representations. To perform perception and control tasks simultaneously, we utilize multi-task learning. Our model comprises of two modules, the first being the perception module that is responsible for encoding the observation data obtained from the RGB-D cameras. It carries out tasks such as semantic segmentation, semantic depth cloud mapping (SDC), and traffic light state recognition. Our approach employs the Convolutional vision Transformer (CvT) \cite{wu2021cvt} to better extract and fuse features from multiple RGB cameras due to local and global feature extraction capability of convolution and transformer modules, respectively. Following this, the control module undertakes the decoding of the encoded characteristics together with supplementary data, comprising a rough simulator for static and dynamic environments, as well as various measurements, in order to anticipate the waypoints associated with a latent feature space. We use two methods to process these outputs and generate the vehicular controls (e.g. steering, throttle, and brake) levels. The first method uses a PID algorithm to follow the waypoints on the fly, whereas the second one directly predicts the control policy using the measurement features and environmental state. We evaluate the model and conduct a comparative analysis with recent models on the CARLA simulator using various scenarios, ranging from normal to adversarial conditions, to simulate real-world scenarios.
Our code is available at \url{https://github.com/pagand/e2etransfuser/tree/cvpr-w} to facilitate future studies.

Title: “Online Probabilistic Model Identification Using Adaptive Recursive MCMC”

Author: P. Agand, H. D. Taghirad, and M. Chen

Abstract: Although the Bayesian paradigm offers a formal framework for estimating the entire probability distribution over uncertain parameters, its online implementation can be challenging due to high computational costs.
We suggest the Adaptive Recursive Markov Chain Monte Carlo (ARMCMC) method, which eliminates the shortcomings of conventional online techniques while computing the entire probability density function of model parameters.
The limitations to Gaussian noise, the application to only linear in the parameters (LIP) systems, and the persistent excitation (PE) needs are some of these drawbacks.
In ARMCMC, a temporal forgetting factor (TFF)-based variable jump distribution is proposed. The forgetting factor can be presented adaptively using the TFF in many dynamical systems as an alternative to a constant hyperparameter. By offering a trade-off between exploitation and exploration, the specific jump distribution has been optimised towards hybrid/multi-modal systems that permit inferences among modes. These trade-off are adjusted based on parameter evolution rate. We demonstrate that ARMCMC requires fewer samples than conventional MCMC methods to achieve the same precision and reliability.
We demonstrate our approach using parameter estimation in a soft bending actuator and the Hunt-Crossley dynamic model, two challenging hybrid/multi-modal benchmarks.
Additionally, we compare our method with recursive least squares and the particle filter, and show that our technique has significantly more accurate point estimates as well as a decrease in tracking error of the value of interest.

Title: “Human Navigational Intent Inference with Probabilistic and Optimal Approaches”

Author: P. Agand, M. Taherahmadi, A. Lim, and M. Chen

Abstract:  Although human navigational intent inference has been studied in the literature, none have adequately considered both the dynamics that describe human motion and internal human parameters that may affect human navigational behaviour. In this paper, we propose a general probabilistic framework to infer the probability distribution over future navigational states of a human. Our framework incorporates an extended Dubins car dynamics to model human movement, which captures differences in human navigational behaviour depending on their position, heading, and movement speed. We assume a noisily rational model of human behaviour that incorporates a) human navigational intent that may change over time, b) how optimal a person’s actions are given the navigational intent, and c) how far ahead in time a person considers when choosing navigational actions.  These parameters are recursively and continuously updated in a Bayesian fashion. To make the Bayesian update and inference tractable, we exploit properties of the time-to-reach value function from optimal control and the extended Dubins car dynamics to construct a utility function on which the human policy is based, and employ particle representations of probability distributions where necessary. We demonstrate the effectiveness of our method by comparing our results with a recent approach using synthetic data and  validate it on real world data.

Title: EcoLight: Reward Shaping in DRL for Environment Friendly Traffic Signal Control

Author: P. Agand, A. Iskrov, and M. Chen

Abstract:

Title: Adaptive Model Learning of Neural Networks with UUB Stability for Robot Dynamic Estimation
Author: P. Agand, and M. Aliyari Shoorehdeli.
Abstract: Since batch algorithms suffer from lack of proficiency in confronting model mismatches and disturbances, an adaptive scheme based on continuous Lyapunov function is driven for online robot dynamic identification. The main contribution of this paper is to propose stable updating rules to drive neural networks inspiring from model reference adaptive paradigm. Network structure consists of three parallel selfdriving neural networks which aim to estimate robot dynamics terms individually. Lyapunov candidate is selected to construct energy surface for a convex optimization framework. Learning rules are driven directly from Lyapunov functions which make the derivative negative. Finally, experimental results on 2-DOF Phantom Omni Haptic device demonstrate efficiency of the proposed method

Title: Decentralized Robust Control for Teleoperated Needle Insertion with Uncertainty and Communication Delay
Author: P. Agand, H. D. Taghirad, and M. Motaharifar.
Abstract: An iterative synthesizing strategy for robust force reflecting control of a Haptic exploration device is proposed. The proposed strategy guarantees the robust stability of the closed loop system with respect to uncertainties caused by the robot dynamics and environmental impedance as well as time-varying communication delays. In order to achieve the stability and performance objectives of the teleoperation system through a multiobjective optimization framework, a suboptimal robust controller is obtained with guaranteed global stability. Under a decentralized structure, the proposed approach provides a systematic design framework using robust approach in the presence of interconnection in the structure. Through experimental results, the improved performance of the proposed approach is demonstrated.

Title: Adaptive recurrent neural network with Lyapunov stability learning rules for robot dynamic terms identification
Author: P. Agand, M. Aliyari Shoorehdeli, and A. Khaki-Sedigh
Abstract: In this paper, a recurrent neural network coupled with Kalman filter is proposed to identify dynamic terms of robotic manipulator. By cooperating some inherent characteristics of robot, this network has the capability to individually identify nonlinear terms using Weighted Augmentation Error (WAE). To present the infrastructure of architecture, an adaptive scheme based on the conventional Back Propagation (BP) is firstly driven using the Gradient Descent (GD) method. Additionally, a stable adaptive updating rule is extracted from the discrete time Lyapunov candidate as an approach for the general nonlinear system identification. Then, this approach is applied to the predefined network. To experimentally validate the computational efficiency and control applicability of the proposed method, Adaptive Neural Network Based Inverse Dynamic Control (ANN-Based-IDC) is employed on a laboratory-scaled twin-rotor CE-150 helicopter. This experiment illustrates enhancement of steady-state performance from 2-to-3 times more in compared with simple PID. Moreover, disturbance rejection and robustness tests admit capability of the method for online dynamic identification in the presence of output and dynamic perturbation

Title: Teleoperation with uncertain environment and communication channel: An ℋ∞robust approach
Author: P. Agand, H. D. Taghirad, and M. Motaharifar.
Abstract: In this paper, a decentralized control structure is proposed based on ℋ∞ robust control synthesis for teleoperated needle insertion in an iterative approach. Since the teleoperation system is subject to unknown time delays in the communication channels, the proposed methodology should be capable of dealing with nonlinearities and uncertainty in environment model and communication channel. The ideal transparency besides robust stability is achieved through a suboptimal solution in an ℋ∞ optimization problem. The method is scrutinized in details for a reality-based model of soft tissues as environment. Simulation results reveal applicability of the proposed methodology for practical implementations.

Title: Particle Filters for Non-Gaussian Hunt-Crossley Model of Environment in Bilateral Teleoperation
Author: P. Agand, H. D. Taghirad, and A. Khaki-sedigh
Abstract: Optimal solution for nonlinear identification problem in the presence of non-Gaussian distribution measurement and process noises is generally not analytically tractable. Particle filters, known as sequential Monte Carlo method (SMC), is a suboptimal solution of recursive Bayesian approach which can provide robust unbiased estimation of nonlinear non-Gaussian problem with desire precision. On the other hand, Hunt-Crossley is a widespread nonlinear model for modeling telesurgeries environment. Hence, in this paper, particle filter is proposed to capture most of the nonlinearities in telesergerie environment model. An online Bayesian framework with conventional Monte Carlo method is employed to filter and predict position and force signals of environment at slave side respectively to achieve transparent and stable bilateral teleoperation simultaneously. Simulation results illustrate effectiveness of the algorithm by comparing the estimation and tracking errors of sampling importance resampling (SIR) with extended Kalman filter.

Title: Transparent & flexible neural network structure for robot dynamics identification
Author: P. Agand, M. Aliyari Shoorehdeli, and M. Teshnehlab
Abstract: In this paper, a novel architecture in multilayer perceptron (MLP) neural network with flexible activation function and adaptive learning rate is presented for a data-driven identification of robot dynamics. It is assumed that the measurement of robot end-effector position, velocity and acceleration are available corrupted by Gaussian noise. Since some general property of robot dynamics are included in the proposed structure as well as optimization indices, this structure is envisaged having good performance in confronting with uncertainty in measurements. The main contribution of this paper is to propose a transparent neural network structure for identification of dynamic terms by introducing a gray-box identifier. Simulation results on 2-DOF serial manipulator reveal the accuracy of the method. Finally, experimental results on a laboratory-scaled twin rotor CE 150 helicopter indicate the applicability of the proposed method.

Title: Vision-based kinematic calibration of spherical robots.
Author:P. Agand, H. D. Taghirad, and A. Molaee
Abstract: In this article, a method to obtain spatial coordinate of spherical robot’s moving platform using a single camera is proposed, and experimentally verified. The proposed method is an accurate, flexible and low-cost tool for the kinematic calibration of spherical-workspace mechanisms to achieve the desired accuracy in position. The sensitivity and efficiency of the provided method is thus evaluated. Furthermore, optimization of camera location is outlined subject to the prescribed cost functions. Finally, experimental analysis of the proposed calibration method on ARAS Eye surgery Robot (DIAMOND) is presented; In which the accuracy is obtained from three to six times better than the previous calibration.