WAWalker Aguilar

Walker Aguilar

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Walker Aguilar has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Monocular vision-based visual control for SCARA-type robotic arms: a depth mapping approach

    by Diego Chambi Tula, Bryan Haladappa Challco, Jonathan Catari, Walker Aguilar, Lizardo Pari

    The accelerated growth of an increasingly automated industry requires the use of autonomous robotic systems. However, the use of these systems commonly requires an enormous amount of sensors. In this paper we evaluate the performance of a new system for visual control of a selective compliance assembly robot arm (SCARA) robotic arm using a monocular depth map that only requires one monocular camera. This system aims to be an efficient alternative to reduce the number of sensors in the robotic arm area while maintaining the effectiveness of traditional vision algorithms that use stereoscopic architectures of cameras. For this purpose, this system is compared with representative state-of the-art vision algorithms focused on the control of robotic arms. The results are statistically analyzed, indicating that the algorithm proposed in this research has competitive performance compared to state-of-the-art robotic arm visual control algorithms only using a single monocular camera.

  • Open Access

    Implementation of a Robotic Arm Control for EOD Applications Using an Immersive Multimodal Interface

    by Walker Aguilar, Lizardo Pari, Yuri Silva, Erasmo Sulla Espinoza, Luis F. Canaza Ccari, Ronald Peña, Nicolás O. Medina

    The advancement of multimodal interfaces aims to provide an intuitive user interface to improve the performance of various tasks. Teleoperated robotics in Explosive Ordnance Disposal (EOD) tasks require the operator to perform complex maneuvering tasks to control a robotic arm. Problems such as loss of depth perception, degradation of visual perception, system delay, and a high mental workload in the control of the robotic elements make these tasks require extensive training periods, extensive knowledge of the robot operation and demand a great effort from the operator to perform a task efficiently and avoid catastrophic situations in handling explosive packages. To solve this, a multimodal interface is proposed based on the creation of a virtual operating environment, where the operator uses a combination of three interfaces: a visual interface through a Virtual Reality Head Mounted Display (VRHMD), a natural user interface (NUI) and a predictive display based interface. The proposed system is evaluated with the participation of thirteen agents with experience in explosive ordnance disposal tasks; the results obtained are divided into objective and subjective results through time measurements of task completion, success rate, usability through System Usability Scale questionnaire (SUS), mental workload through NASA Task Load Index questionnaire (NASA TLX) in Pick and Place tasks, which constitute the primary task type in EOD robotics tasks. The proposed multimodal interface is proven to have a considerably higher efficiency than the conventional keyboard and monitor-based control interface, specifically achieving an improvement in task completion times of 67%. 14%, an improvement in task completion rate of 11.54%, a decrease in overall mental workload of 65.18%, and an improvement in usability of 198.12%.


  • Open Access

    Robust Finite-Time Adaptive Nonlinear Control System for an EOD Robotic Manipulator: Design, Implementation, and Experimental Validation

    by Luis F. Canaza Ccari, Walker Aguilar, Elvis Supo, Erasmo Sulla Espinoza, Yuri Silva Vidal, Nicolás Medina, Lizardo Pari

    To improve the efficiency of human-robot interaction (HRI) in hazardous ordnance manipulation tasks, the design of an advanced control system for a robotic manipulator needs to be investigated. This article presents a robust finite-time adaptive nonlinear control system designed to address the trajectory tracking control of explosive ordnance disposal (EOD) robotic manipulator, considering the actuator dynamics and subject to external disturbances and uncertainties. First, the theoretical design of the controller is developed. In order to achieve fast convergence, high tracking accuracy, and strong robustness, which are fundamental features in EOD applications, a Backstepping Fast Terminal Sliding Mode Control (BFTSMC) strategy is proposed. The sliding surface coefficients are adaptively tuned in real-time by a neural network, where the backpropagation algorithm updates the neural network weight. The combination of the BFTSMC strategy and the adaptive neural network scheme results in the Adaptive Backstepping Fast Terminal Sliding Mode Control (ABFTSMC) strategy, achieving improved control system performance. The stability of the closed-loop control system is demonstrated using Lyapunov theory to guarantee the convergence of tracking errors to the origin in finite time. Next, a detailed description of the hardware system, encompassing sensors, actuators, and controller boards, is provided for the practical implementation of the ABFTSMC strategy. Finally, the proposed control system is experimentally validated through several tests on a real EOD robotic manipulator, and an extensive comparison analysis with other control approaches is performed. The results evidence that the ABFTSMC strategy demonstrates high robustness, fast convergence in finite time, and good tracking accuracy, which are crucial qualities in real-world EOD applications.