CLLE, IRIT  – Toulouse University
Keywords
driving automation, discomfort, drivenger, passenger, scenario

Although it is key to improving acceptability, there is sparse scientific literature on the experience of humans as passengers in partially automated cars. The first study introduced investigated the influence of road type, weather conditions, traffic congestion level, vehicle speed, and human factors (e.g., trust in automated cars) on passenger comfort in an automated car classified as Level 3 according to the Society of Automotive Engineers (SAE). Results showed that comfort was negatively affected by driving in downtown (vs. highway), heavy rain, and congested traffic. Interaction analyses showed that reducing the speed of the vehicle improved comfort in these two last conditions. Results also showed that the most comfortable participants had the higher level of trust in automated cars. This study suggests that optimizing comfort in automated cars should take account of both driving conditions and human profiles. Hence a personalization approach should be favored over a one-for-all.Hence, in a second study, we will investigate the benefits of adapting the behavior of the automated car to the user in a driving simulator experiment. In other words, we will investigate the influence of automated driving style familiarity on automated cars acceptability and take-over performance.


Scientific goal
Improving scientific knowledge in cognitive psychology and ergonomics regarding the interaction between human and automated cars.

Contacts
maxime.delmas_at_univ-tlse2.fr, valerie.camps_at_irit.fr, celine.lemercier_at_univ-tlse2.fr

IRIT, ENAC – Toulouse University
Keywords Predictive Model, Human-Computer Interaction, Mixed Reality
      Mixed Reality has taken off again with the arrival of Head-Mounted Displays. Moreover, mixed reality enables long-term user engagement with the IoT. Nevertheless, the design of a usable system requires many iterations between conception, implementation and evaluation. The use of a predictive model allows usability problems to be detected before implementation. In this project, our predictive model can model the completion time for pointing, validation and selection. First, we defined five new operators. Next, we have computed the unit time for each newly introduced operators. Then, we have consolidated our model through three user studies.Our model can predict the time (± 5%) to complete pointing, validation and selection tasks. 

IRIT , Toulouse University
Keywords Intelligent Transport System, Distributed optimization, Multi-Agent System, Referential Frame Transformation

Recent advancements to improve road traffic have led to the emergence of Intelligent Transport Systems (ITS). Vehicles can replace the human driver in specific context thanks to the ever-increasing number of smart devices, and they gradually become autonomous. As an autonomous entity, a vehicle behaves according to its perceptions provided by embedded sensors. Not only it can see, but it also has access to other vehicles perceptions through communications. There is a necessity for a CAV to perform social interaction and social signaling. The range of potential interlocutors is wide: vehicles, of course, but also other road users: pedestrians, motorcycles, cyclists, electric scooters and if we think ahead, robots. The overall objective is to provide CAVs with social skills making possible cooperative behavior.

The first addressed lock is the transformation of referential frame. A CAV referential frame refers to its environment self-representation. Usually, an autonomous entity uses itself as a reference point. Position, distance, vectors, etc. are calculated from it. This leads to a possible incomprehension between CAVs and the missuses of a critical information. To counter it, we have proposed a solution enabling CAV to understand information from different referential frame.

The second lock concerns the communication optimization in a fleet of CAVs. With the continuously increasing number of vehicles and smart devices, the number of sensed data become huge. Sharing the integrality of these data can cause issues like delays, errors, and bottleneck. Obviously, not everything is useful to share, and we have proposed a solution to optimize which information is shared based on its usefulness.
Figure 1: « A fleet of autonomous and connected vehicles. »

Scientific goals
– Enabling the use of an information from different referential frames
– Addressing the high dynamicity of the ITS
– Optimizing the communication volume and efficiency
Contact
guilhem.marcillaud_at_irit.fr, valerie.camps_at_irit.fr,  stephanie.combettes_at_irit.fr, marie-pierre.gleizes_at_irit.fr

LAAS/CNRS – LCC/CNRS – Laplace, Toulouse University
Keywords E-nose, indoor air quality, multi-gas sensors, nanostructures, metal oxide semiconductors, sensitivity, selectivity, internet of thing (IoT).

Humans spend more than 90% of their time in a closed environment that contains several gaseous pollutants like VOCs (volatile organic compounds). Such gaseous contaminants in the indoor air may cause respiratory problems and chronical diseases. Many others gases such as CO2, CO, and NO2 from urban pollution and poor ventilation systems are also part of indoor air contaminants. Offices, meeting rooms, classrooms and practical workrooms in universities and / or schools may present VOC and /or CO2 levels that exceed the regulatory thresholds. Measuring and monitoring indoor air quality is therefore essential to ensure a better quality life in workspaces. This thesis has been carried out within the framework of the GIS neOCampus (groupement d’intérêt scientifique), led by Université Paul Sabatier UT3 and dedicated to the development of an innovative, connected and sustainable campus for a better quality life. We are interested in the development of miniaturized MOS (metal oxide sensors) gas sensors for the indoor air quality monitoring in offices and classrooms. The objective of this study is to control these pollution levels in order to correct them through measures to ventilate the premises. Making a decision about how to correct air quality is an essential step in the process. As part of this work, we have prepared several prototypes of miniaturized multi-gas sensors (4 sensors) integrated on their electronic card able to detect levels of indoor air pollution. The proximity electronics allows the control and recovery of data from these sensors, and an IOT (internet of things) type communication module based on the WiFi protocol linked to the « Cloud NeoCampus », remotely and wirelessly, generates indoor-air quality signal in real time. This multi-sensor is based on semiconductor sensors based on nanostructured metal oxides (SnO2, WO3, CuO) synthesized at the LCC (laboratoire de chimie de coordination).

Scientific goal
We have developed a new synthetic approach for the nanostructured metal oxides on the sensor platform in order to optimize the performance of the sensitive layer (stability, sensitivity, selectivity). We have studied very efficient associations of n-type and p-type MOS nanostructures based on multilayered implementation on silicon platforms. The gas responses have been measured in laboratories test benches and new measurement protocols (cycled temperature mode versus continuous operation mode) have been defined to selectively detect NO2 or VOCs compounds in air at ppm and sub ppm levels. In addition, PCA (principal components analysis) analyses have been set up to discriminate gas mixtures in test benches.

Contacts
philippe.menini_at_laas.fr, pierre.fau_at_lcc-toulouse.fr, vincent.bley_at_laplace.univ-tlse.fr

IRIT – CNRS , Toulouse University
Keywords Big Data, datalake, big data analytics, IoT, data management, data analysis, open-source, open science, web semantic

IoT data is increasingly integrated into the core of today’s society. Whether you want to analyze a market or a product or study a specific research area, it is increasingly necessary to integrate IoT data but also combine it with massive data produced internally or externally with Open Data. To have a complete vision, it is necessary to integrate both voluminous fast data and numerous small data. Thus, in order to respond to the Vs of Big Data, we have designed an architecture that allows us to manage the Volumetry, Velocity, Variety and Veracity of data to generate Value. This architecture aims at allowing the simple crossing of data whatever the volume, the type or the rate while emphasizing the security of the data, the valorization of these data through the advanced use of the metadata and the use of these metadata through high added value services.
Scientific goals
– Manage any type of data in large volumes with efficiency
– Create value through adequate data modeling
– Enable cross-analysis of heterogeneous data simply in the Big Data context
Contacts
Vincent-Nam.Dang_at_irit.fr / dang.vincentnam_at_gmail.com,  Francois.Thiebolt_at_irit.fr, Marie-Pierre.Gleizes_at_irit.fr
Project repository
https://gitlab.irit.fr/datalake/docker_datalake/
https://github.com/vincentnam/docker_datalake
Scientific Paper
DANG, ZHAO, MEGDICHE, RAVAT (2021), A Zone-Based Data Lake Architecture for IoT, Small and Big Data. IDEAS 2021, to appear. (DOI: 10.1145/3472163.3472185 / ISBN : 978-1-4503-8991-4/21/07)

IRIT and Laboratoire d’Aérologie, Toulouse University
Keywords Bicycle traffic, Urban mobility, Air quality, Urban pollution, Agent based simulation, Synthetic population

Excessive concentrations of pollutants in the urban air are regularly observed, posing a long-term danger to the health of inhabitants. Monitoring the quality of urban air is therefore a very important issue to help stakeholders to take appropriate measures (reduction of road traffic…). The urban spatial distribution of air pollution is very heterogeneous and evolves rapidly over time. It is therefore important to develop reliable, fast, and spatially spread measurement methods. This last criterion is often hard to implement. For example, air quality measuring stations are very accurate, but their measurements are too local to obtain information on areas with no station.

In this work, we propose to study the usage of residents’ daily bicycle traffic as a participatory network of air quality sensors, providing volunteer cyclists with an air quality sensor to use during their daily commute. To evaluate the effectiveness of such a network, we choose to build a multi-agent simulation based on the GAMA development environment that models a group of bicycle-mounted sensors mapping urban air quality. Traces of urban air quality collected by the sensors are then used to infer air quality at the city level. Results are compared with actual data from public air administration.

The model simulates the daily mobility of a synthetic population of cyclists in the city. Travel and pollution data are generated based on several real data sources (mobiloscope, private companies, and bicycle sensors). Observations recorded along the bike trips are complemented by geographical information (height of buildings, natural areas, distance to highway, …) that are obtained through Geographical information systems (GIS) and further used as predictor variables in a land use regression (LUR) model.

The dataset of synthetic information is used to infer a critical number of bicycles that would be required for an optimal assessment of the intra-urban air quality. To this end, we process the collected pollution data, for each time step, with extrapolation algorithms (eg. LUR) of the measured pollution concentrations and the city environment. For example, the distance of a point to primary roads is a relevant indicator for determining NO2 concentration. Thus, by performing a regression to estimate the relationship between the distance to the main roads and NO2 concentration, we can predict the NO2 concentration at unmeasured points. Moreover, the impact of the cyclists’ circadian rhythm on the monitoring of the daily cycle of pollutants is investigated. We also evaluate the opportunity for cross-calibrating the mobile sensors during the biker’s Rendez-vous based on the daily agenda of the different biker categories.



Scientific goal
The objective is to understand how well a network of bicycle-mounted sensors could map air quality in urban areas.
Contact
Nathan.coisne_at_student.isae-supaero.fr, jean-francois.leon_at_isae-supaero.fr, nicolas.verstaevel_at_irit.fr, benoit.gaudou_at_irit.fr, elsy.kaddoum_at_irit.fr

IRIT, Toulouse university
Keywords LoRaWAN, CubeCell, Arduino, neOCampus end-devices

The neOSensor series of end-devices may be seen as a simple, efficient and cheap way to interface sensors with the neOCampus IoT infrastructure. Previously focusing on WiFi networks, ESP8266 and ESP32 based neOSensor experienced many limitations due to the (very) short range of WiFi network (especially when you’re located within basements or ways too high regarding WiFi gateways).

To overcome these limitations, we decided to design a brand new LoRaWAN version based on the Heltec CubeCell module. This one provides native battery and solar panel support while being programmed through the Arduino IDE … enabling us to share many of our libraries between these two different releases. Open-source and designed with KiCad, you can build your own neOSensor 🙂