TI expands assisted driving chip line with Jacinto 7

Jacinto 7 chips from Texas Instruments are designed to help future cars with processing the enormous amounts of data used in assisted driving. (Texas Instruments)

Chipmakers are focused more than ever on the safety of future vehicles equipped with assisted driving and autonomous technologies.

On Tuesday, Texas Instruments showed a small group of reporters and analysts attending CES 2020 more than a dozen safety-related use cases that rely on two new Jacinto 7 processors. One of the System-on-Chip designs focuses on providing an efficient gateway for cars that connect over wireless to a range of inputs, while the other is devoted to Advanced Driver Assistance Systems (ADAS).

Both chips can be programmed from a single software development kit by design teams at vehicle manufacturers and evaluation modules are now available for $1,900 each. Both chips were built on a 12nm process.

Fierce AI Week

Register today for Fierce AI Week - a free virtual event | August 10-12

Advances in AI and Machine Learning are adding an unprecedented level of intelligence to everything through capabilities such as speech processing and image & facial recognition. An essential event for design engineers and AI professionals, Engineering AI sessions during Fierce AI Week explore some of the most innovative real-world applications today, the technological advances that are accelerating adoption of AI and Machine Learning, and what the future holds for this game-changing technology.

The TDA4VM processor for ADAS requires just 5 to 20 watts of power, meaning no special cooling technology will be required. Also, front-facing cameras of 8-megapixel resolution can be supported or four to six 3 megapixel cameras, while also fusing inputs from radar, LiDAR and ultrasonic on a single chip.

Such capabilities will allow for automated parking, with surround view and image processing for large displays that might be used in future car cockpits. The new DRA829V processor for a vehicle’s communications gateway uses an industry-first PCIe switch on-chip and integrates an eight-port gibabit Ethernet switch for fast performance computing.

With the performance improvements in the new chips, sensors can be used to detect objects on the road in higher resolutions and at greater distances than before, improving to 150 meters, up from 80 meters.

Curt Moore, general manager of Jacinto processors at TI, said with 1.3 million car deaths a year globally, ADAS and autonomous vehicles will make a difference. He cited data from the Institute for Highway Safety showing that automatic emergency braking features alone can reduce half of all front-to-rear collisions. 

With sensors being added all the time to new vehicles, the latest models of cars now operate with 150 million lines of code, an increase of 15 times over the size of the data stream in cars built in 2016, Moore said. That explosion in data alone increases the need for more efficient chips. 

* TI also showed off innovations that don't rely on Jacinto chips at CES.  Engineers demonstrated how car sensors running on the chips can support a hand gesture to open a pickup’s tailgate or can be used to dim headlights selectively to keep a portion of the view well-lit, while dimming the portion of the beam that shines on the oncoming car.

* Other demonstrations showed how a holographic image can be projected on the interior of the front window just below a driver’s field of view, to bring instrument readings closer. A rear-seat baby monitor demonstration showed how sensors can detect a baby’s breathing, motion or crying in the rear seat to prevent a driver from leaving the child behind.

RELATED: Qualcomm launches Snapdragon Ride for assisted and self-driving

* An earlier version of this story incorrectly said these innovations relied on Jacinto chips.  

Suggested Articles

One forecast from Cameron Chell: the best AI designers of the future won’t come from top universities

Survey of 30 chipmakers offers a good sign for research and development of self-driving vehicles, analyst says

Engineers are discovering that AI can be used very efficiently for a variety of voice command and amplification applications