Driverless Tata Nano, First Driverless car from India! #madeinIndia Dr. Roshy John decided to build a 'Driverless' car, and chose the cheapest car in the world to do so; the Tata Nano and did the unthinkable. Apple and Google beware, this man looks like a Genius. Before we get into the details of the build, just watch this surreal video of the Tata Nano driving itself!
A Ph.D in Robotics from National Institute of Technology, Dr. John began thinking about this project about 5 years back. For him, the need for autonomous driving arose when he was returning back from the airport in a taxi and realised the driver was too fatigued to drive and he has to take the wheel. Since then, Roshy and his team have been working on this project. With no significant help from anyone, initially they did not know where to start. With the sad state of Indian roads, the erratic traffic and pedestrian hazards it is rather difficult to even think about driverless cars!
The idea behind choosing the Nano, is due to the fact that it is the smallest rear-engined car on sale. And it also boasts of good interior space for the sensors and actuators. Also, the data available through the OBD II port of the Nano was well readable and the data could be easily be processed by the servers and actuators which were to be placed in the car. Using the same concept as they do in testing robots, Dr. John created a simulation concept, before prototyping it in real life. This let him keep costs at a minimum and achieve the following : - All physical parameters of the road and surrounding can be simulated - Physical design and Driverless algorithms can be worked on through CAD and changed dynamically, without increasing development cost of the hardware. - Test Cases/Scenarios can be run continuously - All sensors and actuators can be replicated inside the simulation - In the Simulation, most real world roads can be created and 'driven' on. The team did not consist of any experts in this domain, rather it was a bunch of enthusiastic engineers who were bored of their monotonous work. They decided to work late nights and weekends on this project of passion.
Here are the notes of the development of the Tata Nano driverless car from Dr. Roshy John's blog:
We got the sensor datasheets from the sensor manufacturer’s websites and we re-created it inside the simulator, with the same data protocol and in the connectivity sense. A life size virtual TATA Nano was created inside the simulator referring the product brochures available on TATA Motors website. The driving algorithms worked on a separate workstation and the simulation on a graphics intensive workstation. Both these workstations were connected together using a TCP/IP network. We tried so many hours of simulation, test case execution and failure modes. We did simulations for over 8 months, by which I was over 70% sure that this concept is going to work. By that time my financial side was also getting better. I was inventing a lot of stuff and started receiving incentives and royalties for the patents filed. My then company gave incentives and perks apart from salary for the patents granted. The excitement was tremendous which made me think about continuing this research on a real TATA Nano with real sensors. I bought a TATA Nano and totally reverse engineered it to understand how to hack into the vehicle’s electronics to connect sensors, actuators and engine scanners. The major difference with simulation is that, we considered the vehicle to be having automatic transmission, but back then TATA Nano had only manual transmission. The initial task we took up initially was to convert the manual transmission to automatic – which is now known as “Automated Manual Transmission”. The concept of driverless cars is not yet legalized in India. Thus, all the road tests were done on secluded residential projects – thanks to the non-occupied villa projects where the builders construct well defined asphalt roads before constructing houses. We did the initial pilot testing on these roads where the car did limited self-driving. We continued this research over these years and made a driving robot modular which can be fitted on to any vehicle. I have also filed the patents protecting the concept. These days, almost all the automotive manufacturers are continuing with their own research on autonomous vehicles. This could lead to the development of new standards and new insurance models. But surprisingly, I find teaching the old dog new tricks (an autonomous driving robot) more fun. Over and above, using simulation reduces the development investments to a bare minimum
For now, it looks very promising and we could safely assume that this man and his vision for the future are going to go places. Watch this space for latest updates on this great innovation and the team behind it.
I bought a TATA Nano and totally reverse engineered it to understand how to hack into the vehicle’s electronics to connect sensors, actuators and engine scanners. The major difference with simulation is that, we considered the vehicle to be having automatic transmission, but back then TATA Nano had only manual transmission. The initial task we took up initially was to convert the manual transmission to automatic – which is now known as “Automated Manual Transmission”..
This is quite an achievement considering the development time it has taken. Google's self-driving car also looks strangely similar to the Nano. Only here, Dr. John has had to deal with two things - one an internal combustion engine. Google uses an electric motor, which is more compact and easier to deal with. Two, a manual transmission - Dr. John has had to convert the manual transmission into an AMT - which itself is quite a task. AMTs have only caught on in the past couple of years with the Celerio, Nano, TUV, Zest and now the Dzire. The Tata Nano AMT came in only last year. It would have been far easier working with an existing AMT car. In the face of all that, this is quite a feat. And when he says he can shift the system to any car, that is commendable - which means it is modular. Awesome!
This is the kind of news that needs to be shared, but most people are still obsessed over other silly stuff. Am surprised that I didn't see any facebook posts about this. Even launch of KUV100 was getting more publicity than this great feat.
Wow! I'm hooked! This is indeed a great achievement! I have always felt that if a driverless car can successfully drive in the mean streets of Pune, or even B'lore, Mumbai or Delhi... it can drive anywhere in the world.
While Dr. Roshy John and team take their time fine-tuning the Tata Nano driverless car for India, Singapore is all ready to debut a fleet of driverless cabs this week! These are modified Mitsubishi iMiEV and Renault Zoe cars. See: https://www.zigwheels.com/forum/post...t-in-singapore
As much as I love driving, autonomous vehicles, at least for people who dread driving, would make roads much safer. And while there is still long way to go before we see full autonomy, the impact could be much bigger that what we are anticipating at the moment. The automobile companies will be the worst hit. Many people are already ditching ownership in favour of sharing services like Uber or Zoomcar and autonomous vehicles will further catalyse that. People won't buy another car just for their wives at home to go shopping in afternoon. Ford, GM, Honda, Toyota, Volvo, PSA, BMW they are all investing in sharing+rental companies as well as startups developing driverless solutions because they know that the industry is about to change and they don't want to face the fate of Kodak when it does. I work in travel and during various conferences, I see the airline industry stakeholders already discussing how autonomy in vehicles could affect short haul flights. Real estate could also be affected as with more efficient urban transport, the significance of living near the urban center would go down. Just some of my far fetched theories. Would like to know your thoughts. Btw CorsaVeloce would it be possible for you to connect me to Dr. Roshy John?
Akshay_Sharma, what you're saying its absolutely right, but lets not forget that while it may take 10 years for autonomous driving to become a thing, India will still be 20 years behind that. Our Metropolitan cities are yet to get proper metro connectivity and given the driving conditions, most of the integrated transport plans have failed in the past. Really looking forward to see Dr. John adapt his home-built Nano to the traffic conditions here. The last time we spoke, he was working with TATA Motors on a car which he was keeping under wraps. And ya, surely I could connect you with him.
[QUOTE_NODE]"Originally posted by Akshay_Sharma" As much as I love driving, autonomous vehicles, at least for people who dread driving, would make roads much safer. And while there is still long way to go before we see full autonomy, the impact could be much bigger that what we are anticipating at the moment. [/QUOTE_NODE]
"Originally posted by Akshay_Sharma" As much as I love driving, autonomous vehicles, at least for people who dread driving, would make roads much safer. And while there is still long way to go before we see full autonomy, the impact could be much bigger that what we are anticipating at the moment.
Very true. Not many people have actually given what kind of impact that these vehicles will make a thought. The thing is there are so many other things that need to be sorted out before these vehicles become a reality. For example, who is to be blamed in case of an accident - the passengers or the manufacturer? For now, major manufacturers trying up with ride sharing services seem like a very good idea. Not only does it help curb congestion and pollution, it also makes fret less about their daily commute making them more relaxed at home and the workplace. No? Like CorsaVeloce mentioned, I don't think these vehicles are coming to India anytime soon considering our road conditions and poorly planned cities. But I wish they would come sooner as it would be really good fun seeing cars run into each other. Imagine what would happen if these cars actually learn from their drivers. Then we'll see autonomous cars overtaking from the left and blocking bikers on the road all the time
CorsaVeloce Actually I wasn't speaking exactly with India or any timelines in mind. I was just shooting random theories on the potential impact and was speaking more with the western markets in mind. In India it is going to be a different level of challenge. My head fails to process the unpredictable traffic here, it would be far too long before AI is capable enough to do that. And when it arrives, it is more likely to come from people who understand the Indian conditions better and will be able to gather enough data to use for the systems. Uber is a strong player in the rush for driverless cars. They are sitting on heaps of data about driving patterns all over the world which they are leveraging in their projects with Volvo and others. Their drivers are adding data of 1.2 billion miles per month, lot of data for a starting point. By the way I connected with Dr. John on LinkedIn in the meantime. Appreciate your help.
NikilSJ On the topic of car sharing, Volvo is doing a really good job with Sunfleet. Volvo introduced the keyless entry system with the option of using mobile phone as a key. Few months back they started a pilot project with Sunfleet, eliminating the need of handing over physical keys for renting out cars. Find their video below: [youtube_video]https://www.youtube.com/watch?v=FF6JtS3y1xA[/youtube_video] And you are absolutely right about the liability thing. I read a really interesting piece on TechCrunch on that topic. Will add that here when I find.
Akshay_Sharma Even Ford has been doing their part lately. Their project is called Ford Smart Mobility. On August 16th this year, they announced that they are serious about having a high-volume, fully autonomous vehicle for ride sharing by 2021. Ford has said that they are collaborating with four startups to enhance its autonomous vehicle development. They are also doubling their tech team in Silicon Valley and Palo Alto. Below is a little blurb from their website: “The next decade will be defined by automation of the automobile, and we see autonomous vehicles as having as significant an impact on society as Ford’s moving assembly line did 100 years ago,” said Mark Fields, Ford president and CEO. “We’re dedicated to putting on the road an autonomous vehicle that can improve safety and solve social and environmental challenges for millions of people – not just those who can afford luxury vehicles.” [youtube_video]https://youtube.com/watch?v=lITdVxm_hD0[/youtube_video]
Kaiserketkar Add some unfamiliar names to that NuTonomy, Nauto, Drive.ai, Cruise automation, Oxbotica, Comma,ai, Otto. Actually most of the major automakers are working with these small companies, partly because they are agile and partly to avoid the hassle of starting fresh in this space.