There’s no doubt in how Artificial Intelligence is redefining the human lives. Taking the thriving nature of AI as an inspiration, Fisheyebox Innovation Lab (Fisheyebox) was formed. Fisheyebox is a team of scientists, researchers, programmers, designers and automotive enthusiasts trying to make an AI for Good. The team at Fisheyebox is fundamentally working on human inspired driving and highly intelligent urban mobility solution. It does not intent to build cars, it wants to make them intelligent and more connected in an affordable way. Fisheyebox’s work ranges, from high level driving behavior modeling, robotic scene estimation to low level driving firmware actuation for universal compatibility. The company has developed an all-in-one solution for an intelligent drive system which can be interfaced with any automotive grade drive-by-wire platform in the world. It’s the brain for the autonomous and connected vehicles. Also, as more and more cars are now having drive-by-wire systems by default, it will be able to develop a “snap-on” Level 5 auto-pilot in the not too distant future.
How the Idea was Generated?
This origin of the idea was started a couple of years back, when the autonomous technology was just in R&D after completion of its primary level research in the field of computer vision and image processing along with Artificial Intelligent area. The existence of drive by wire system of the newly designed and developed car added an extra flavor of an advantage in this idea. Fisheyebox is super-enthusiastic about self-driving cars, after drive-by-wire platform was invented to fit high-level logic. That was the start of it all. The company ended up working in a garage and came up with the prototype finally. Thus, making this technology for the world market is a challenging story which Fisheyebox has tried its best to develop in the real-world road scenario in India.
Fisheyebox has worked on an Auto-Pilot capable of autonomously navigating a car in a cluttered urban environment. It was involved in the development of a highly-robust Perception Module for sensing and estimation of the environment around the vehicle from vast vocabulary of visual cues (explicit and implicit) such as drivable road space, lane markings, traffic lights, to moving obstacles (both static and dynamic) such as vehicles and pedestrians, all by using sensor fusion camera data and Deep Learning techniques include Scene Segmentation, Object Detection and Localization.
The company has also worked on areas such as sensor self-calibration, vehicle ego-motion, perception, mapping and localization using a variety of sensor modalities (Camera, Radar, INS, GPS, Odometry). It was also involved in the development of a highly precise Navigation Module for localization of the vehicle on a centimeter scale accuracy. Besides, it was also involved in the high-level programming of embedded systems for interfacing robotic actuation with the vehicle and worked on real-time programming of embedded platforms, automotive ECUs, automotive Ethernet/ CAN controllers.
The Fisheyebox’s DriveX package comes with a black-box hardware package mentioned above, on top of which runs a sophisticated Artificial Intelligence Operating System (OS) which acts as an human-machine interface between the driver and the vehicle, to self-diagnose repairs and communicate with other vehicles but also manage their internal environment, managing each passenger’s preference for entertainment and work productivity. That is valuable time drivers will re-acquire once relieved of the attention burdens of driving. On the road, everyone will get more hours back in their day to do what they want and not stress out in traffic. The OS technically turns the vehicle into an intelligent and connected ecosystem.
The OS features a highly intelligent Vehicle Diagnostic System (VDS) capable of analysing in-vehicle telematics and repair data in order to predict and prevent problems before they result in mechanical failure. With the VDS running on-board, the company would be capable of transforming the entire automotive ownership experience by identifying problems more quickly, reduce unplanned maintenance, improve customer service, lower warranty costs through more accurate diagnoses, and offer diagnostic services tailored to each vehicle/owner. Its state-of-the-art AI algorithms can detect driving behavior patterns from drifting, braking and accelerations that indicate potential danger, coupled with biometric data directly from the driver inside the vehicle, and processes it by making required adjustments autonomously in the driving actuation that would help keep it safer or help navigate dangerous driving conditions. And yes, it does come with an intelligent Personal Assistant capable of engaging in natural language conversation with the vehicle occupants. From key-less Voice Encrypted Start, to guiding you the best route to your destinations, to playing your preferred music, calling your contacts, to all auxiliary controls it does it all.
A Thought Leader
The inceptive mind behind Fisheyebox is Pinaki Laskar, the CEO & Founder of the company. A disruptive Innovator & Cognitive Technologist, Pinaki has been founding brain for many disruptive AI solutions ranging from Autonomous Car and Intelegent Transport System (ITS), AI-based Music and Retail. He is an expert and distinguished Inventor in Artificial Intelligence and IIOT with research in AI and Ethics. As a thought leader he has been speaker at various conferences including ‘Make in India’, Mumbai, TIE – Bangalore, Sevan Startup Summit – Armenia, Neural Networks Conference – Finland, Artificial Intelligence International Conference – Barcelona, Cloud Expo – Silicon Valley, USA and many more with a work experience of two decades. Currently, He is leading AI for business transformation & Innovation by design thinking using technology as a catalyst.
In the near future, Fisheyebox will work on perfect design and DNA of building smart Intelligent autonomous car, the one without conventional Non- Steering Gear, brakes or accelerator and The OS which will feature a high performance microkernel architecture, with an enhanced kernel-level security, encryption, access control and fault tolerance, to make it almost impossible to compromise.
Currently working on Prospective customer for autonomous vehicles and Advance Driving System with Pre – AV (Pre – Autonomous Vehicles) System. The company is also striving to enable vehicle manufacturers procure vehicle middleware solutions from Fisheyebox rather than invest in their own research and development, including existing vehicle owners who would like to purchase the middleware solution as a plug-and-play system.
After being confined to researchers, academia and non-profit organizations for over a decade, Google is opening access of its Earth...Read more