Search Results

Increasing electrification of the vehicle as well as the demands of increased connectivity presents automotive manufacturers with formidable challenges. Automakers and suppliers likely will encounter three practices that will influence how they develop and manufacture highly connected vehicles and future e-mobility platforms: 1) hierarchical production processes in fixed footprints that do not share data freely; 2) lack of real-time, in-line quality inspection and correction processes for complex miniaturized electronic components; and 3) floor to enterprise resource and execution systems that can collect, analyze and respond to rapidly changing production needs.

Applications using industrial robotics have typically led to establishing a safeguarded space encompassing a wide radius around the robot. Operator access to this hazard zone was restricted by a combination of means, such as hard guarding, safeguarding, awareness means, and personal protective equipment. The introduction of collaborative robots is redefining safeguarding requirements. Many collaborative robots have inherently safe designs that enable an operator and a robot to work within a shared, collaborative workspace. New technology in industrial robotics has opened up opportunities for collaborative operation. Collaborative operation could include either industrial or collaborative robots, depending on its application. The current defined modes of collaborative operation are hand guiding; speed and separation monitoring; safety-rated monitored stop; and, power and force limiting.

As batteries become a major component of numerous advanced vehicles, significant efforts have been allocated towards characterizing and estimating battery energy capability over the lifetime of a vehicle. Currently, battery State of Charge (SOC) is one of the primary values used for this characterization; however SOC usage has several issues when implemented in Electric Vehicle (EV), Hybrid Electric Vehicle (HEV), and Plug-In Hybrid Electric Vehicle (PHEV) systems. One of the main issues with reporting battery SOC as a characterization of battery energy capability is that it only gives a percentage of the energy available to the operator. SOC does not accurately represent the true capability or capacity of the battery, and thus fails to account for the impact to capability with respect to battery size, age, and recent operational history.

A key strategy to improving the real-world fuel consumption and emissions of medium and heavy duty vehicles is the hybridization of these applications. Unlike the passenger vehicle market, medium and heavy duty applications are typically comprised of a range of components from a variety of manufacturers. The vocational market diversity and size places considerable demand on fuel efficiency and emission compliance. Medium and heavy duty applications have the ability to be successfully hybridized in ways that are not currently, or would not be practical within a passenger vehicle. This would also drive greater truck and bus vertical integration of the hybrid components. However, medium and heavy duty manufacturers have been prevented from certifying a full vehicle level platform due to the current engine only certification requirements.

A key strategy to improving the real-world fuel consumption and emissions of medium and heavy duty vehicles is the hybridization and alternative fueling of these applications. Unlike the passenger vehicle market, medium and heavy duty applications are typically comprised of a range of components from a variety of manufacturers. The current diversity and size of the market, as well as their applications demands considerable thought with regards to fuel efficiency and emission compliance. Medium and heavy duty applications have the ability to be successfully hybridized and fueled in ways that are not currently, or would not be practical within a passenger vehicle. This drives increased vertical integration of the propulsion and accessory components. However, medium and heavy duty manufacturers have been prevented from certifying a full vehicle level platform due to the current engine certification requirements.

Replacing a human driver is an extraordinarily complex task. While machine learning (ML) and its’ subset, deep learning (DL) are fueling breakthroughs in everything from consumer mobile applications to image and gesture recognition, significant challenges remain. The majority of artificial intelligence (AI) learning applications, particularly with respect to Highly Automated Vehicles (HAVs) and their ecosystem have remained opaque - genuine “black boxes.” Data is loaded into one side of the ML system and results come out the other, however, there is little to no understanding at how the decision was arrived at. To make these systems accurate, these AI systems require lots of data to crunch and the sheer computational complexity of building these DL based AI models also slows down the progress in accuracy and the practicality of deploying DL at scale.