Artificial intelligence device company BrainChip Holdings (ASX: BRN) has taken an affirmative step towards integrating its Akida neuromorphic chip into autonomous vehicles after signing a binding joint development agreement with European automotive supplier Valeo Corporation.
The agreement means both companies will collaborate to develop a new wave of tech solutions based on artificial intelligence (AI) and reduced power consumption within the overarching theme of miniaturisation that’s taking the tech industry by storm.
According to BrainChip, the Akida chip is a neural networking processor that “brings artificial intelligence to the edge” above and beyond what existing technologies can do.
The company said its Akida solution is high-performance, small, ultra-low power and enables a wide array of edge capabilities that include continuous learning and inference.
In April this year, BrainChip introduced its first event-based neural-network intellectual property and neuromorphic system-on-chip (SoC) device – the AKD1000 – which enables AI capability in edge AI systems at ultra-low power consumption.
Alongside AKD1000, the Akida neural processor represents the next generation of AI that canto overcome the limitations of legacy AI chips, which require too much power and bandwidth to handle the needs of today’s applications. Moreover, Akida is expected to move the technology forward in a significant leap, allowing AI to do more with less.
“Our AKD1000 is able to deliver the portability, connectivity and processing power needed for AI edge applications without retraining the entire network,” BrainChip chief development officer Anil Mankar said.
This latest agreement between BrainChip and Valeo has been hailed as a validation of the company’s Akida device by a Tier-1 sensor supplier and “considered to be a significant development”, according to BrainChip.
In a statement to the market this morning, BrainChip said Valeo will utilise Akida and collaborate on the development of neural network processing solutions, for integration in autonomous vehicles (AVs).
The terms of the deal stipulate that both companies must reach specific performance milestones, with BrainChip stating it expects to receive payments to cover its expenses, subject to the completion of, as yet, undisclosed milestones.
The dawn of Akida
As part of the ongoing design of driver assistance systems and AVs, the issue of timely data processing is paramount.
Accurate real-time data processing is essential for AVs to be deemed safe and reliable; however, the amount of data being generated continues to increase exponentially, thereby making efficient data processing elusive and problematic.
BrainChip is hoping to reconcile the need for greater processing ability with greater amounts of data by developing what it calls “neuromorphic” technology that can handle more data quicker while using less power than existing components.
Neuromorphic engineering was first developed by US scientist Carver Mead in the 1980s and refers to the use of very-large-scale integration (VLSI) systems containing electronic analogue circuits to mimic neuro-biological architectures present in the nervous system.
According to BrainChip, by combining the Akida neural network processor with sensors, the resulting system can achieve ultra-low power, minimum latency, maximum reliability and incremental learning.
“This is a major advancement over current architectures which require large amounts of data to be transmitted to a CPU or GPU, which has the burden of processing all data from all sensors and then combining the results to make a decision or retrain the network for new classifiers,” the company said.
Today’s news pushed BrainChip shares up by 36% to $0.12 per share in morning trade.