Khaled Khnissi

Khaled Khnissi

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 April 2022 in International Journal of Intelligent Transportation Systems Research
Verified
Journal Article
Closed access
PDF file
KKKhaled Khnissi
Khaled Khnissi
CJChiraz Ben Jabeur
Chiraz Ben Jabeur
HSHassen Seddik
Hassen Seddik

1 September 2020 in Robotics and Autonomous Systems
Verified
Journal Article
Closed access
KKKhaled Khnissi
Khaled Khnissi
CJChiraz Ben Jabeur
Chiraz Ben Jabeur
HSHassene Seddik
Hassene Seddik

1 October 2018
Verified
Conference Paper
Closed access
KKKhaled Khnissi
Khaled Khnissi
CSChiraz Seddik
Chiraz Seddik
HSHassen Seddik
Hassen Seddik
The field of autonomous navigation of mobile robot is advancing so fast especially with the development of machine learning algorithms. This study aims to introduce a neural network controller that controls the trajectory and the obstacle avoidance of a non-holonomic mobile robot.We train the robot in environment containing multiple obstacles with different places. This paper includes both a kinematic and a dynamic study of a mobile robot. Different training schemes have been studied that tackle the learning objectives differently. The trained controller is producing the Pulse Width Modulation (PWM) signals that could be implemented in a microprocessor and validated by simulations. Unlike some other recent approaches, this work was validated by a 3D simulation which is similar to the real model.

1 July 2019
Verified
Conference Paper
Closed access
KKKhaled Khnissi
Khaled Khnissi
CJChiraz Ben Jabeur
Chiraz Ben Jabeur
HSHassene Seddik
Hassene Seddik
This paper presents the implementation of a mobile robot in 3D environment. A non-holonomic mobile robot (TurtleBot Burger 3) is designed to navigate following different trajectories by controlling its motors, and it is expected to be useful to test autonomous navigation algorithm. The study of a non-holonomic mobile robot is so difficult due to the complexity of its mathematical description. Therefore, this paper introduces a simulator based on the geometrical structure of the robot. After that, a 3D mobile robot is built and simulated in Matlab-Simscape environment. Different schemes of tracking trajectories have been introduced in this work to study the behaviour of the mobile robot. The purpose of this 3D environment is to create a hostile environment with random obstacles and it optimize the path tracking of the robot. The proposed simulation modelling is valuable to give a clear understanding of complex systems and it will help to have a correct digital representation of the robot.

1 April 2025 in Research Square
Verified
Preprint
Open access
PDF file
CJChiraz BEN Jabeur
Chiraz BEN Jabeur
HSHassen Seddik
Hassen Seddik
KKKhaled Khnissi
Khaled Khnissi
AHAhmad Hably
Ahmad Hably
Pursuit evasion game (PEG) belongs to dynamic differential games, which have received a lot of attention thanks to its ability to articulate many real-life applications such as military, aerospace and mobile robotics. Several mathematical tools and processes are used to solve such problems, but recent techniques relying on deep reinforcement learning (DRL) have gained popularity, in particular DRL techniques adapted for problems with continuous action spaces such as Deep Deterministic policy gradients (DDPG). Most of these studies use two-phase training approach, where in the first phase only the pursuer is trained on a fixed trajectory of the evader, and in the second phase both DRL agents are trained simultaneously. The first phase of this approach requires trajectory generation, which introduces bias, but it remains adapted to unbound game areas. On the other hand, DDPG, is known to suffer from value overestimation problem, which led to the introduction of twin delayed DDPG (TD3). A tiny portion of the scientific literature use TD3 in the case of a one vs one pursuit evasion game, especially in the case of a bounded game area and without relying on a two-phase training approach. This paper explores the case of one-to-one pursuit evasion game in a constrained game area, using two TD3 agents trained simultaneously and from scratch via self-play only. Several rewards are proposed, which when combined, improve the training. Three training alternatives are presented, considering a normal self-play case, a case with a buffer zone and a final case with noisy actions. The three alternatives proved to output similar results, where both the pursuer and the evader agents were able to find optimal control strategies without any human intervention or trajectory generation. The simulation showed that the agents were performing better than other conventional methods such as Non-linear Model Predictive Control (NMPC). This study proposes a novel framework for a one-on-one PEG in a constrained environment, leveraging self-play to train two TD3 agents simultaneously and from scratch. Theoretical contributions include designing a multi-faceted reward function that integrates game status, evolution, duration, and agent performance to enhance training. Practical contributions involve evaluating three training configurations normal self-play, self-play with a buffer zone, and noisy actions—and demonstrating their effectiveness. Results show that all configurations enable the agents to discover optimal strategies autonomously, outperforming conventional methods like Non-linear Model Predictive Control (NMPC). Simulations reveal the agents' intelligent behaviors, with the pursuer leveraging game constraints and the evader executing evasive maneuvers. Comparison with existing methods highlights superior capture time and adaptability to noise, paving the way for real-world implementations.