Tag Archives: Autonomous

Intel Introduces Loihi – A Self Learning Processor That Mimics Brain Functions

Intel has developed a first-of-its-kind self-learning neuromorphic chip – codenamed Loihi. It mimics the animal brain functions by learning to operate based on various modes of feedback from the environment. Unlike convolutional neural network (CNN) and other deep learning processors, Intel’s Loihi uses an asynchronous spiking model to mimic neuron and synapse behavior in a much closer analog to animal brain behavior.

loihi - Intel's self-learning chip
Loihi – Intel’s self-learning chip

Machine learning models based on CNN use large training sets to set up recognition of objects and events. This extremely energy-efficient chip, which uses the data to learn and make inferences, gets smarter over time and does not need to be trained in the traditional way. The Loihi chip includes digital circuits that mimic the brain’s basic mechanics, making machine learning faster and more efficient while requiring much lower computing power.

The chip offers highly flexible on-chip learning and combines training and inference on a single chip. This allows machines to be autonomous and to adapt in real time instead of waiting for the next update from the cloud. Compared to convolutional neural networks and deep learning neural networks, the Loihi test chip uses many fewer resources on the same task. Researchers have demonstrated learning at a rate that is a 1 million times improvement compared with other typical neural network devices.

The self-learning capabilities prototyped by this test chip have huge potential to improve automotive and industrial applications as well as personal robotics – any application that would benefit from the autonomous operation and continuous learning in an unstructured environment. For example, recognizing the movement of a car or bike for an autonomous vehicle. More importantly, it is up to 1,000 times more energy-efficient than general purpose computing.

Features

  • Fully asynchronous neuromorphic many core mesh.
  • Each neuron capable of communicating with thousands of other neurons.
  • Each neuromorphic core includes a learning engine that can be programmed to adapt network parameters during operation.
  • Fabrication on Intel’s 14 nm process technology.
  • A total of 130,000 neurons and 130 million synapses.
  • Development and testing of several algorithms with high algorithmic efficiency for problems including path planning, constraint satisfaction, sparse coding, dictionary learning, and dynamic pattern learning and adaptation.

Role Of Vision Processing With Artificial Neural Networks In Autonomous Driving

In next 10 years, the automotive industry will bring more change than we have seen in the last 50, due to technological advancement. One of the largest changes will be the move to autonomous vehicles, usually known as the self-driving car. Scientists from many universities are striving to implement vision processing with the artificial neural network to provide driver assistance in self-driving cars.

vision processing
Vision processing using convolutional artificial neural networks

Vision processing, as well as artificial neural networks, have been around for many years. Convolutional artificial neural networks (CNN) are sets of algorithms that extract meaningful information from sensor input. CNN’s are very computationally efficient at analyzing a scene. They are also able to identify objects as cars, people, animals, road signs, road junctions, road marking etc. enabling them to determine the relevant reality of the scene. As this system runs in real-time, the decision can be made as soon as the sensing part is complete.

One of the major steps in visual environment understanding for automotive applications is key points tracking and estimating ego-motion and environment structure subsequently from the trajectories of these key points. A propagation based tracking (PBT) method is popularly used to obtain the 2D trajectories from a sequence of images in a monocular camera setup.

The inputs from one or all of the sensors like LIDAR, RADAR, camera, IR, etc. are evaluated and decisions are taken accordingly. For example, if a car in the front suddenly brakes, the onboard computer would instantly verify the distance and calculate the speed with help of the existing sensors. Then it would apply the brakes faster than any human would be able to do. This method helps to prevent an accident with 90% efficiency.

The use of vision processing with CNN is rapidly increasing in automotive applications to enable camera-based autonomous driving. This technology sets a new driving standard. With this technology in our hand, fewer accidents, fewer fatalities, and less pollution are experienced. Vision processing in autonomous driving also enables efficient journeys, reduced crowding, car sharing, and packing cars in more tightly via vehicle to vehicle communication.