Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 5
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Data Homogenization Method for Heterogeneous Sensors Applied to Reinforcement Learning

  • Palacios-Morocho, Maritza Elizabeth
  • López-Muñoz, Pablo
  • Costán, Manuel A.
  • Monserrat del Río, Jose Francisco|||0000-0001-8664-6408
[EN] In autonomous navigation and route planning, the data obtained by the different sensors play a significant role. On the one hand, more data will lead to faster learning of the behavioral policy. On the other hand, agents equipped with different sensors will need more computing power to process the data, thus requiring more robust equipment and increasing the cost of implementation. In addition, the complexity of the algorithms increases as different types of data, i.e., data with different structures, have to be synchronized. Therefore, this paper addresses the problem of homogenization and synchronization of data provided by heterogeneous sensors. Furthermore, it presents a novel method of estimating data in order to provide the agent with a 360-degree view of the environment, similar to that provided by a laser. The method's performance compares the different behavioral policies obtained by different viewing angles of a camera with the policy obtained by a laser. The data obtained from the different viewing angles of each sensor are used in a path planning algorithm, which was designed to use a single 24-scan laser as an input source. The results show that the proposed method is robust since the behavior policies can be reused regardless of the viewing angle with which the sensor (camera) is provided. Furthermore, the proposed novel algorithm achieves an average efficiency of 68% and 94% using a 90 and 360-degree camera, respectively., The work of Elizabeth Palacios-Morocho was supported by the Research and Development Grants Program, Universitat Politecnica deValencia, under Grant PAID-01-19.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Enhancing Cooperative Multi-Agent Systems With Self-Advice and Near-Neighbor Priority Collision Control

  • Palacios-Morocho, Maritza Elizabeth
  • Inca-Sánchez, Saúl Adrián
  • Monserrat del Río, Jose Francisco|||0000-0001-8664-6408
[EN] The coordination of actions to be executed by multiple independent agents in a dynamic environment is one of the main challenges of multi-agent systems. To address this type of scenario, a key technology called Reinforcement Learning (RL) has emerged, which enables the training of optimal cooperative policies among agents. However, traditional value decomposition methods suffer fromunstable convergence when the number of agents increases. To address this problem, this article proposes a novel algorithm based on centralized learning that employs a self-advice module to replace the joint action, thereby reducing the algorithmic complexity. The proposed algorithm uses the Joint Action Learning (JAL) concept to find an optimal approach and a collision controller module that was designed to further mitigate the risk of collisions. A comparison of the algorithm proposed is carried out with two benchmark algorithms. The first one focuses on ecomposing the reward signal and the second one trains a different actor-critic network for each agent. Furthermore, multiple target points are defined to enhance cooperative scenarios during the learning process. According to the results, the proposed approach outperforms the two benchmarks by 8% and 49%, thus highlighting the effectiveness of the centralized learning approach in multi-agent systems., Elizabeth Palacios s research was supported by the Research and Development Grants Program under Grant PAID-01-19 of the Universitat Politècnica de València.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Performance Evaluation of Onboard Processing Capability Reduction in Cooperative Vehicles Using 5G and Artificial Intelligence

  • Palacios-Morocho, Maritza Elizabeth
  • Inca-Sánchez, Saúl Adrián
  • Monserrat del Río, Jose Francisco|||0000-0001-8664-6408
[EN] Fifth Generation (5G) technology is one of the keys to the industrial revolution known as Industry 4.0 since it provides faster connectivity and allows a greater number of devices to be connected simultaneously. In the transport sector, newly produced vehicles are equipped with various sensors and applications to help drivers perform safe maneuvers. However, moving from semi-autonomous to fully autonomous vehicles to cooperating systems remains a major challenge. Many researchers have focused on Artificial Intelligence (AI) techniques and the ability to share information to achieve this cooperative behavior. This information can be made up of different data, which can be obtained from different sensors such as Laser Imaging Detection and Ranging (LiDAR), radar, camera, Global Positioning System (GPS), or data related to the current speed, acceleration, or position. The combination of the different shared data is performed depending on the approach of each navigation algorithm. This data fusion will allow a better understanding of the environment but will overload the network, as the traffic generated will be massive. Therefore, this paper addresses the challenge of achieving this cooperation between vehicles from the point of view of network requirements and computational capacity. In addition, this study contributes to advancing theory into real-world practice by examining the performance of cooperative navigation algorithms in the midst of the migration of computational resources from onboard vehicle equipment to the cloud. Specifically, it investigates the transition from a cooperative navigation algorithm based on a decentralized architecture to a semi-decentralized one as computationally demanding processes previously performed onboard are performed in the cloud. Additionally, the paper discusses the indispensable role of 5G in fulfilling the escalating demands for high throughput and low latency in these services, particularly as the number of vehicles increases. The results of the tests show that the AI acting alone cannot achieve optimal performance, even using 100% of the computational capacity of the onboard equipment in the vehicle. However, a system that integrates 5G and AI-based joint decisions can achieve better performance, reduce the computational resources consumed in the vehicle, and increase the efficiency of collaborative choices by up to 83.3%, Elizabeth Palacios s research was funded by the Research and Development Grants Program (PAID-01-19) of the Polytechnic University of Valencia.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Multipath Planning Acceleration Method With Double Deep R-Learning Based on a Genetic Algorithm

  • Palacios-Morocho, Maritza Elizabeth
  • Inca-Sánchez, Saúl Adrián
  • Monserrat del Río, Jose Francisco|||0000-0001-8664-6408
[EN] Autonomous navigation is a well-studied field in robotics requiring high standards of efficiency and reliability. Many studies focus on applying AI techniques to obtain a high-quality map, a precise localization, or improve the proposed trajectory to be followed by the agent. As traditional planning methods need a high-quality map to obtain optimal trajectories, this paper addresses the problem of multipath map-less planning, and proposes a novel multipath planning algorithm (Double Deep Reinforcement Learning - Enhanced Genetic (DDRL-EG)) for mobile robots in an unknown environment. It combines Double Deep Reinforcement Learning (DDRL) with Heuristic Knowledge (HK), Experience Replay (ER), Genetic Algorithm (GA), and Dynamic Programming (DP), allowing the agent to reach its target successfully without maps. In addition, it optimizes the training time and the chosen path in terms of time and distance to the target. A hybrid method is also used in which Semi-Uniform Distributed Exploration (SUDE) is employed to determine the probability that the action is decided based on directed knowledge, hybrid knowledge, or autonomous knowledge. The performance of DDRL-EG is compared with two other algorithms in two different environments. The results show that DDRL-EG is a more robust and powerful algorithm since with less training, it can provide much smoother and shorter trajectories to the target., The work of Elizabeth Palacios was supported by the Research andDevelopment Grants Program (PAID-01-19) of the Universitat Politecnica de Valencia.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Millimeter-wave Human Blockage Model Enhancements for Directional Antennas and Multiple Blockers

  • Prado-Alvarez, Danaisy|||0000-0003-3781-5951
  • Inca-Sánchez, Saúl Adrián
  • Martín-Sacristán, David|||0000-0002-7781-557X
  • Monserrat del Río, Jose Francisco|||0000-0001-8664-6408
[EN] The Third Generation Partnership Project (3GPP) has defined a blockage model as an add-on feature to the channel model used in its evaluations of the physical layer in the 0.5-100 GHz frequency range. This letter focuses on the human body blockage losses in the millimeter-wave band proposing: (i) a new criterion to place the diffraction points over the edges of the blockers that considers the precise position of the blocker with regard to the line-of-sight between the transmitter and the receiver, (ii) a specific criterion to determine which potential blockers, from a set of human bodies present in a certain scenario, should be considered effective blockers given the positions of a transmitter, a receiver, and those bodies, and (iii) a modification of the model to provide more accurate estimations in the case in which several blockers are closely located. The validity of our criteria and the accuracy improvement are confirmed by a set of measurements performed at 30 GHz with directional antennas and with multiple human blockers in different positions., The work of Danaisy Prado-Alvarez was supported by the H2020 Marie Curie Program, with Project Grant No. 766231 WAVECOMBE-ITN-2017. Part of this work has been performed in the framework of the H2020 project 5G-SMART co-funded by the EU. This was also supported by the Spanish Ministry of Science, Innovation and University under the project RTI2018-099880-B-C31. The associate editor coordinating the review of this letter and approving it for publication was J. Choi.