Pablo Marín-Plaza

Dr. Pablo Marín-Plaza

Mechanical engineering

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
22 February 2018 in Journal of Advanced Transportation
Verified
Journal Article
Open access
PDF file
PMPablo Marín-Plaza
Pablo Marín-Plaza
Ahmed HusseinAhmed Hussein
Ahmed Hussein
David Martin GomezDavid Martin Gomez
David Martin Gomez
Arturo De La EscaleraArturo De La Escalera
Arturo De La Escalera
The aim of this work is to integrate and analyze the performance of a path planning method based on Time Elastic Bands (TEB) in real research platform based on Ackermann model. Moreover, it will be proved that all modules related to the navigation can coexist and work together to achieve the goal point without any collision. The study is done by analyzing the trajectory generated from global and local planners. The software prototyping tool is Robot Operating System (ROS) from Open Source Robotics Foundation and the research platform is the iCab (Intelligent Campus Automobile) from University Carlos III. This work has been validated from a test inside the campus where the iCab has performed the navigation between the starting point and the goal point without any collision. During the experiment, we proved the low sensitivity of the TEB method to variations of the vehicle model configuration and constraints.

4 May 2022 in IEEE Access
Verified
Journal Article
Open access
SNSheida Nozari
Sheida Nozari
ALI KRAYANIALI KRAYANI
ALI KRAYANI
PMPablo Marín-Plaza
Pablo Marín-Plaza
LMLucio Marcenaro
Lucio Marcenaro
David Martin GomezDavid Martin Gomez
David Martin Gomez
Carlo S. RegazzoniCarlo S. Regazzoni
Carlo S. Regazzoni
Classical imitation learning methods suffer substantially from the learning hierarchical policies when the imitative agent faces an unobserved state by the expert agent. To address these drawbacks, we propose an online active learning through active inference approach that encodes the expert’s demonstrations based on observation-action to improve the learner’s future motion prediction. For this purpose, we provide a switching Dynamic Bayesian Network based on the dynamic interaction between the expert agent and another object in its surrounding as a reference model, which we exploit to initialize an incremental probabilistic learning model. This learning model grows and matures based on the free-energy formulation and message passing of active inference dynamically at discrete and continuous levels in an online active learning phase. In this scheme, generalized states of the learning world are represented as distance-vector, where it is the learner’s observation concerning its interaction with a moving object. Considering the distance vector entail intentions, it enables action prediction evaluation in a prospective sense. We illustrate these points using simulations of driving intelligent agents. The learning agent is trained by using long-term predictions from the generative learning model to reproduce the expert’s motion while learning how to select a suitable action through new experiences. Our results affirm that a Dynamic Bayesian optimal approach provides a principled framework and outperforms conventional reinforcement learning methods. Furthermore, it endorses the general formulation of action prediction as active inference.

19 February 2020 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
DKDivya Thekke Kanapram
Divya Thekke Kanapram
FABIO PATRONEFABIO PATRONE
FABIO PATRONE
PMPablo Marín-Plaza
Pablo Marín-Plaza
Mario MarcheseMario Marchese
Mario Marchese
EBEliane Lucia Bodanese
Eliane Lucia Bodanese
Carlo S. RegazzoniCarlo S. Regazzoni
Carlo S. Regazzoni
The advancements in connected and autonomous vehicles in these times demand the availability of tools providing the agents with the capability to be aware and predict their own states and context dynamics. This paper presents a novel approach to develop an initial level of collective awareness (CA) in a network of intelligent agents. A specific collective self-awareness functionality is considered, namely agent-centered detection of abnormal situations present in the environment around any agent in the network. Moreover, the agent should be capable of analyzing how such abnormalities can influence the future actions of each agent. Data-driven Dynamic Bayesian Network (DBN) models learned from time series of sensory data recorded during the realization of tasks (agent network experiences) is here used for abnormality detection and prediction. A set of DBNs, each related to an agent is used to allow the agents in the network to reach synchronously aware about possible abnormalities occurring when available models are used on a new instance of the task for which DBNs have been learned. A Growing Neural Gas (GNG) algorithm is used to learn the nodes variables and conditional probabilities linking nodes in the DBN models; a Markov Jump Particle Filter (MJPF) is employed for state estimation and abnormality detection in each agent using learned DBNs as filter parameters. Performance metrics are discussed to asses the algorithm’s reliability and accuracy. The impact is also evaluated by the communication channel used by the network to share data sensed in a distributed way by each agent of the network. The IEEE 802.11p protocol standard has been considered for communication among agents. Performances of the DBN based abnormality detection models under different channel and source conditions are discussed. The effects of distances among agents and of the delays and packet losses are analyzed in different scenario categories (urban, suburban, rural) Real data sets are also used acquired by autonomous vehicles performing different tasks in a controlled environment.

26 April 2019 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
DCDamian Campo
Damian Campo
MBMohamad Baydoun
Mohamad Baydoun
PMPablo Marín-Plaza
Pablo Marín-Plaza
David Martin GomezDavid Martin Gomez
David Martin Gomez
LMLucio Marcenaro
Lucio Marcenaro
Carlo S. RegazzoniCarlo S. Regazzoni
Carlo S. Regazzoni
This paper proposes a method to detect abnormal motions in real vehicle situations based on trajectory data. Our approach uses a Gaussian process (GP) regression that facilitates to approximate expected vehicle's movements over a whole environment based on sparse observed data. The main contribution of this paper consists in decomposing the GP regression into spatial zones, where quasi-constant velocity models are valid. Such obtained models are employed to build a set of Kalman filters that encode observed vehicle's dynamics. This paper shows how proposed filters enable the online identification of abnormal motions. Detected abnormalities can be modeled and learned incrementally, automatically by intelligent systems. The proposed methodology is tested on real data produced by a vehicle that interacts with pedestrians in a closed environment. Automatic detection of abnormal motions benefits the traffic scene understanding and facilitates to close the gap between human driving and autonomous vehicle awareness.

16 April 2020 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
MRMahdyar Ravanbakhsh
Mahdyar Ravanbakhsh
MBMohamad Baydoun
Mohamad Baydoun
DCDamian Campo
Damian Campo
PMPablo Marín-Plaza
Pablo Marín-Plaza
David Martin GomezDavid Martin Gomez
David Martin Gomez
Carlo S. RegazzoniCarlo S. Regazzoni
Carlo S. Regazzoni
The technology for autonomous vehicles is close to replacing human drivers by artificial systems endowed with high-level decision-making capabilities. In this regard, systems must learn about the usual vehicle's behavior to predict imminent difficulties before they happen. An autonomous agent should be capable of continuously interacting with multi-modal dynamic environments while learning unseen novel concepts. Such environments are not often available to train the agent on it, so the agent should have an understanding of its own capacities and limitations. This understanding is usually called self-awareness. This paper proposes a multi-modal self-awareness modeling of signals coming from different sources. This paper shows how different machine learning techniques can be used under a generic framework to learn single modality models by using Dynamic Bayesian Networks. In the presented case, a probabilistic switching model and a bank of generative adversarial networks are employed to model a vehicle's positional and visual information respectively. Our results include experiments performed on a real vehicle, highlighting the potentiality of the proposed approach at detecting abnormalities in real scenarios.

7 December 2021 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
HIHafsa Iqbal
Hafsa Iqbal
DCDamian Campo
Damian Campo
PMPablo Marín-Plaza
Pablo Marín-Plaza
LMLucio Marcenaro
Lucio Marcenaro
David Martin GomezDavid Martin Gomez
David Martin Gomez
Carlo S. RegazzoniCarlo S. Regazzoni
Carlo S. Regazzoni
This paper proposes an algorithm to model and process streams of LiDAR data under an autonomous vehicle framework. LiDAR is assumed to be an exteroceptive sensor that allows the vehicle to have dynamic 3D scene perception of its surroundings. We employ an encoder-decoder architecture based on 3D-Convolutional layers called 3D Convolution Encoder-Decoder (3D-CED), together with a transfer learning strategy to extract a set of features from point clouds, which are relevant in the context of autonomous driving. The resulting features allow to make inferences of the future point cloud data and detect multiple abstraction level anomalies in controlled scenarios by utilizing a probabilistic switching dynamic model called High Dimensional Markov Jump Particle Filter (HD-MJPF). Moreover, a comparison is provided between piecewise linear, piecewise nonlinear, and nonlinear predictive models for anomaly detection at multiple abstraction levels. Our approach is evaluated with data collected from the LiDAR sensors of the autonomous vehicle while performing certain tasks in a controlled environment.