Based on the components developed by LeddarTech, GlobalSensing Technolgies and Intempora this videos shows how 3D sensor data input to neural network plus sensor data and video fusion make possible object tracking and classification
Facial Recognition Increases Autonomous Vehicles Safety
Transitioning between Autonomous and Manual Driving
With autonomous and semi-autonomous vehicles on the roads, the booming industry of automated vehicles has been a hot topic. Tesla Motors Inc. is selling vehicles with a semi-autonomous “Autopilot” feature across the country. Uber Technologies Inc., the ride-hailing giant, has recently begun trials with driverless cars in Pittsburgh. And there are several other companies investing large amounts of money to make the autonomous vehicles a reality.
However, for the time being, the autonomous technology is mainly designed to be used on highways. The system may disengage the autopilot under various conditions such as freeway exits. The autopilot needs to manage the hand-over between the automated and the manual modes. To have a smooth hand-over, it is important to make sure that the driver is alert and ready to take control of the car before the autopilot is disengaged.
ERTRAC Automated Driving Roadmap
This document provides an overview on the current status for Automated Driving technologies with regard to implementation in Europe. The ERTRAC roadmap is based on available documents for automated driving. The overall objective is to identify challenges for implementation of higher levels of automated driving functions. A lot of work has been done on this topic by various stakeholders and multi-stakeholders platforms (e.g. iMobility Forum, EUCAR, CLEPA, ERTICO, EPoSS) and in European research projects. Therefore, it is essential to avoid any duplication of activities and concentrate on the missing items, concerns and topics for future implementation. Automated Driving is seen as one of the key technologies and major technological advancements influencing and shaping our future mobility and quality of life. The main drivers for higher levels of Automated Driving are: • Safety: Reduce accidents caused by human errors. • Efficiency and environmental objectives: Increase transport system efficiency and reduce time in congested traffic. Smoother traffic will help to decrease the energy consumption and emissions of the vehicles. • Comfort: Enable user’s freedom for other activities when automated systems are active. • Social inclusion: Ensure mobility for all, including elderly and impaired users. • Accessibility: Facilitate access to city centres. Automated Driving must therefore be considered as a key aspect for the European Transport policy, able to support several objectives and societal challenges, such as road safety, decarbonisation, smart cities, social inclusiveness, etc. In technological terms, the advancement towards highly Automated Driving is seen as an evolutionary process to ensure that all involved stakeholders can develop and evolve with the adequate pace. This process already started with the development of ABS, ESP and Advanced Driver Assistant Systems (ADAS) and will progressively apply to more functions and environments. In parallel, driverless automated systems can be deployed to provide transport solutions in restricted areas with dedicated infrastructure or at specific locations e.g. airports. The European community is nevertheless facing important challenges to enable or implement higher levels of Automated Driving in all environments. It is utmost important that these challenges and existing gaps (technology, legislation, regulatory, policy, etc.) are early recognized and appropriate measures are taken. Europe has a very strong industrial basis on automotive technologies and systems. The automotive industry is the largest private investor of R&D in Europe: four out of the TOP5 companies investing most in R&D in Europe are automotive companies. Various studies revealed the outstanding economic impact projected for automated driving for the years to come ranging up to €71bn in 20301 , 2. The estimated global market for automated vehicles is 44 million vehicles by 20303. The economic impact is realised through economic growth, new jobs across the automotive value chain, and wider economic impacts such as increased productivity, reduced time in congestion, reduced number of severe accidents (reduced number of fatalities), efficiency gains in the transport system (i.e. increased capacity and reduced fuel consumption), etc. The whole industrial sector needs to evolve and adapt in a fast pace to stay ahead in global competitiveness while including all stakeholders and addressing societal needs. 1 KPMG, Connected and Autonomous Vehicles – The UK Economic Opportunity 2 Boston Consulting Group (2015) Revolution in the Driver’s Seat: The Road to Autonomous Vehicles 3 Autonomous Vehicles, Navigant Research, Aug/13 2. Scope and Objectives 5 Some challenges are beyond the scope of a research roadmap, but their clearance is key to a future exploitation of the R&D results, and to reach the objective to establish a European lead market and technology leadership. To name just the most obvious one, legislation and regulatory framework must be adapted according to the technological advancement. Further, industrialisation is key for implementation of automated driving and to realise the positive economic impact. In order to avoid another ‘developed in Europe but produced outside’ scenario, a pan-European effort with high visibility and recognition is required. ERTRAC, the European Road Transport Research Advisory Council, acknowledges its important role to ensure a harmonised approach towards implementation of higher levels of Automated Driving functionalities. In 2014, ERTRAC established a task force with stakeholders and experts from its member associations and individual members to define a joint roadmap for Automated Driving. The document is structured in Scope and Objectives, Common Definitions and Deployment Paths, State of the Art including an overview on the current EU and international situation, the Key Challenges and the ERTRAC Roadmap for Automated Driving.
Trucking Industry Gets a Glimpse of its Automated Future at CES 2017
The heavy- and light-duty trucking industries will benefit from the automated driving technologies rolling out of the 2017 Consumer Electronics Show this week in Las Vegas.
Automated trucking innovators Peloton Technology and partner FEV North America Inc., a smart-vehicle technology business, are demonstrating so-called SAE Level 1 truck platooning technology, which allows tightly contained, digitally connected packs trucks to drive in formation to cut wind resistance and save fuel.
“If you can apply autonomous driving to the trucking industry, there’s tremendous opportunity for reducing costs and for making it easier for drivers,” said Stephanie Brinley, an analyst at IHS Markit.
The Society of Automotive Engineers, or SAE, uses a classification system of six different levels of vehicle autonomy based on the amount of necessary driver intervention. Level 1 requires a driver to be ready to take control at any time, and features a combination of radar-controlled advanced driver assistive systems, or ADAS, like adaptive cruise controls for “feet off” operations and land keep assist for “hands off” use.
Tesla’s spanking-new radar technology has apparently taken the safe-driving lesson to heart. And the evidence is startling: Check out the video of a developing accident on a Dutch roadway that was recently captured on the dashcam of a Tesla Model X. The camera captured it BEFORE the Tesla driver even knew it was coming. How? The Tesla’s Autopilot’s forward collision warning system was able to see the car in front of the car in front of the Tesla
In the video embedded here, we can hear the Tesla Autopilot’s Forward Collision Warning sending out an alert for seemingly no reason, but a fraction of a second later we understand why when the vehicle in front of the Tesla crashes into an SUV that wasn’t visible to the Tesla driver, but apparently was fto the Autopilot’s radar. Autopilot then started braking before the driver could apply the brakes himself.
One of the main features enabled by the new radar processing capacity is the ability for the system to see ahead of the car in front of you and basically track two cars ahead on the road. The radar is able to bounce underneath or around the vehicle in front of the Tesla Model S or X and see where the driver potentially cannot because the leading vehicle is obstructing the view.
Tata Elxsi Showcases Advanced Automotive Technology Solutions at CES 2017
ata Elxsi, a global design and technology services company and a leader for automotive electronics and software engineering services, is showcasing key solutions addressing Autonomous Vehicle, Connected Infotainment, Automation, IoT and Artificial Intelligence at CES 2017.
Key solutions being showcased at CES 2017 include:
Autonomous Vehicle & ADAS
Autonomai: Tata Elxsi's advanced autonomous vehicle middleware platform, with deep learning and AI capabilities, is designed to help OEMs and system suppliers build, test and deploy customizable autonomous vehicle applications.
Autonomai's modular architecture comprises of Perception, Guidance Navigation & Control and Drive-by-wire systems. It includes algorithms for key aspects such as lane, vehicle & pedestrian detection, path planning, sensor fusion, object tracking, GPS/INS-based vehicle state estimation, 3D mapping and localization.
Autonomai supports integration of a combination of sensor technologies such as LiDar, Radar, Ultrasonic sensors and Mono/Stereo cameras to suit customer requirements. It comes pre-integrated with extensive validation datasets, and support for AI and deep learning to enable the autonomous vehicles of the future.
Technologies for Connected Car
e-cockpit is Tata Elxsi's connected cockpit software solution that integrates Instrument Cluster, Head Unit, Heads Up display and ADAS on a single system-on-chip, driving ECU consolidation while supporting advanced features such as fast boot, 3D animated dials and support for a wide set of HMI tools including QT, GL Studio and Kanzi.
This solution uses hypervisor to allow separation of critical and non-critical functions, and integrates ASIL-B compliant functionality for key vehicle information and ADAS applications.
The connected car showcase also includes GENIVI 10.0 compliant infotainment architecture with enhanced cyber-security and OTA capability, and telematics and IoT related engineering and services for vehicle health management and value-added services.
Tata Elxsi's V2X Emulator provides real-time emulation of both car-to-car and car-to-infrastructure scenarios for real-time traffic and wireless channel conditions. The tool emulates multiple on-board and roadside units, allowing OEMs and suppliers to extensively test and validate their ECUs and systems in a lab environment, which would otherwise be very difficult, expensive, and unsafe to recreate in road testing.
Automotive Sensors Enabling Advanced Vision, Awareness, and Emergency Response Systems Will Experience Strong Growth as Automakers Embrace Systems for Improved Safety and Vehicle Autonomy
The market for advanced driver assistance systems (ADAS) is on the verge of a tipping point. Driven largely by a quest for improved safety, either via government mandates or a desire to receive top-tier crashworthiness ratings, automakers are rapidly incorporating new technologies and systems that are designed to help drivers avoid accidents by improving their situational awareness, improving reaction times, or enhancing the vehicle’s response to adverse conditions. Key components that are enabling ADAS include cameras, image processors, system processors, ultrasonic sensors, solid-state lidar, high-end lidar, radar sensors, and infrared sensors, among others.
According to a new report from Tractica, ADAS component shipments will increase at a healthy pace over the next decade, rising from 218.1 million units shipped in 2016 to 1.2 billion units by 2025. By that time, the market intelligence firm forecasts that the ADAS component market will reach $89.3 billion in annual revenue.
CES 2017: Nasa’s helping Nissan make driverless cars
Nissan’s autonomous car drive has gained significant momentum at the CES show in Las Vegas. The Japanese carmaker has put a timeline to its plans, and confirmed the MkII Leaf – due in the next year or two – will get semi-autonomous functionality as standard.
It has also collaborated with Nasa to help develop something called SAM (Seamless Autonomous Mobility) that means proper self-driving vehicles – taxis and vans with no drivers in them at all – won’t be completely stranded when an accident or construction work ahead of them blocks the road.
The idea is that actual humans will monitor the vehicles’ progress – the head of a fleet of autonomous cabs, for example – and if a car gets confused by a road layout, it’ll pause, send its human an alert, and they’ll use its cameras and location to guide it around obstacles and back on track.
You might ponder the point of a self-driven car if it can’t entirely drive itself. Nissan’s CEO Carlos Ghosn is fairly bullish about the fact that it’s a long time before our road networks will consist purely of driverless cars.
European Commission : MOBILITY AND TRANSPORT - Road Safety
The opinions expressed in the studies are those of the consultant and do not necessarily represent the position of the Commission.
Advanced Driver Assistance Systems (ADAS) can provide personal assistance in a road environment that cannot always take into account the possibilities and limitations of the older driver. An analysis of the strengths and weaknesses of the older driver has shown that the most important need for support stems from the difficulties that older drivers have to:
- Judge whether fellow road users are approaching the same intersection and at what speed
- Notice other road users while merging and changing lanes
- Notice traffic signs and signals
- React quickly in a complex traffic situation.
These difficulties stem from functional limitations such as a decrease in motion perception, peripheral vision, flexibility of head and neck, selective attention, and speed of processing information and decision making. ADAS that can compensate for these limitations, can contribute to a reduction of the crash involvement of older drivers. Such ADAS should have one or more of the following functionalities :
- Draw attention to approaching traffic
- Signal road users located in the driver's blind spot
- Assist the driver in directing his attention to relevant information and/or
- Provide prior knowledge on the next traffic situation .
ADAS that have these functionalities could improve the safety of older driversSearch for available translations of the preceding linkIT•••. Examples of such systems are collision warning systems aimed at intersections and in-vehicle signing systems. There are, however, also ADAS that could improve the mobility of the older driverSearch for available translations of the preceding linkIT•••, or may reduce his injury severitySearch for available translations of the preceding linkIT•••. Examples of those systems are vision enhancement systems and mayday systems.
Using ADAS to improve the safety or mobility of the driver involves more than making sure that the supported subtask is carried out safely. It also involves that the support provided does not have any negative effects on the other elements of the driving task. Examples of negative side effectsSearch for available translations of the preceding linkIT••• are increased task load due to a bad design of the human machine interface, and the effects of behavioural adaptation. ADAS that could improve road safety for older drivers.