Navigating Occluded Intersections with Autonomous Vehicles using Deep Reinforcement Learning Artificial Intelligence

Providing an efficient strategy to navigate safely through unsignaled intersections is a difficult task that requires determining the intent of other drivers. We explore the effectiveness of Deep Reinforcement Learning to handle intersection problems. Using recent advances in Deep RL, we are able to learn policies that surpass the performance of a commonly-used heuristic approach in several metrics including task completion time and goal success rate and have limited ability to generalize. We then explore a system's ability to learn active sensing behaviors to enable navigating safely in the case of occlusions. Our analysis, provides insight into the intersection handling problem, the solutions learned by the network point out several shortcomings of current rule-based methods, and the failures of our current deep reinforcement learning system point to future research directions.

How Automotive AI Is Going to Disrupt (Almost) Every Industry - DZone AI


With almost every automaker on the planet launching predictions about the arrival date of driverless vehicles, we here at Arcbees are willing to bet that you've given at least a little thought to what that utopian future would be like napping, watching a movie, or getting work done in the backseat while your car deals with traffic. And how exciting would it be never to have to parallel park again? Ford & Argo AI claim they'll be "fully autonomous" by 2021 Hyundai, which is prioritizing affordability, has announced its goals for autonomous freeway driving by 2020 and the more complex navigation of urban driving by 2030. Elon Musk of Tesla, on the other hand, is characteristically audacious and ambitious, already offering many driver-assist AI features and promising full automation, via a tweet, in "3 months maybe, 6 months definitely" -- meaning by the end of 2017. When it comes to AI-driven autonomous vehicles, however, it's important to understand the terminology.

How Sensors and Analytics are Transforming Traffic 7wData


By Judith Hurwitz, President & CEO, Hurwitz and Associates In cities everywhere, traffic congestion leads to frustration, lost productivity, inefficiencies in commerce and delays in emergency responses. Traffic is a challenge that has frustrated planners, administrators, and citizens for decades; progress, when it has been achieved, has been very limited. Now, however, a confluence of better and more affordable sensor technology, improved networking, and powerful real-time analytics and machine learning are putting major city improvements within reach. Cities can be defined as layers of complex systems that have to work in collaboration with each other to function successfully. Computer models and day-to-day experience can provide some guidance for helping things to run smoothly, but only some.

Demystifying AI: Understanding the human-machine relationship


The artificial intelligence of today has almost nothing in common with the AI of science fiction. In "Star Wars," "Star Trek" and "Battlestar Galactica," we're introduced to robots who behave like we do -- they are aware of their surroundings, understand the context of their surroundings and can move around and interact with people just as I can with you. These characters and scenarios are postulated by writers and filmmakers as entertainment, and while one day humanity will inevitably develop an AI like this, it won't happen in the lifetime of anyone reading this article. Because we can rapidly feed vast amounts of data to them, machines appear to be learning and mimicking us, but in fact they are still at the mercy of the algorithms we provide. To illustrate this in grossly simplified terms, imagine a computer system in an autonomous car.

No reason to fear the robot revolution - TechCentral


Basically, machine learning uses algorithms that iteratively learn from data, meaning that it enables computers to find hidden insights without being explicitly programmed where to look. However, where data mining extracts information for human comprehension, machine learning uses it to detect patterns in data and to adjust its program actions accordingly. Incredibly, it's a science that is not new; it is one that was, in fact, predicted nearly 70 years ago by Alan Turing, widely considered the father of theoretical computer science and artificial intelligence. For starters, it is applicable to healthcare, as machine learning algorithms can process more information and spot more patterns than humans can, by several orders of magnitude.

Nvidia's slightly terrifying Metropolis platform paves the way for smarter cities


The company's Metropolis intelligent video analytics platform applies deep learning to constantly process and contextualize the masses of data streaming from the ever-increasing number of cameras watching us every day. This platform encompasses a number of Nvidia products all operating on a unified architecture, which can come together to analyze and make sense of video in real time. Nvidia's Metropolis platform encompasses a number of Nvidia products all operating on a unified architecture (Credit: Nvidia) Through partner businesses, Nvidia's technology is set to take things even further, enabling autonomous aerial systems streaming video back from the sky, security robots driving themselves around looking for trouble spots, and ultra high resolution, super-wide panoramic cameras that capture a whole scene instead of needing to track and follow objects. Nvidia presented its Metropolis intelligent video analytics platform, along with some 20-odd demos of its partner applications, at last month's International Security Conference and Expo in Las Vegas.

How is predictive data shaping the auto industry


How is predictive data changing the automotive industry and what changes can we expect to see in the future? Connected and autonomous cars are going to benefit most from the inclusion of predictive data because their design centers on data collection and processing. As more and more connected cars hit the roads, data management is going to become an essential tool. Predictive data has already shown potential for preventative maintenance, but this same application could be used to predict software problems and security flaws as well.

Repurposing 1980s traffic systems for artificial intelligence


Video monitoring systems for traffic have been in use since the mid- 1960s, initially pioneered by Israel and the Netherlands in order to capture motorists violating traffic light regulations. But they would have been very differently-designed if computer evaluation, rather than human monitoring, had been anticipated – a problem which researchers from Carnegie Mellon are currently tackling. The sheer scale and maturity of urban traffic-monitoring systems, many of which hail back to the 1980s, are a tantalising prospect for AI in terms of generating usable data about traffic flow, but are predicated on'common sense' – currently an elusive goal for machine learning, even in terms of widely-agreed definition. In the paper Understanding Traffic Density from Large-Scale Web Camera Data four researchers consider what Fully Convolutional Networks (FCNs) might be able to achieve in terms of leveraging all this extant, live data without the need to invest in expensive and experimental new monitoring systems. City-wide traffic camera networks were originally developed as tools for municipal traffic authorities to make rough estimations of congestion, and to be apprised of serious blockages such as road accidents; any traffic flow data emerging from their use would be purely anecdotal – impossibly expensive or complicated to rationalise and analyse scientifically.

Autonomous driving - do it yourself!


ALV (Autonomous Land Vehicle) project used lidar sensors, computer vision and robotic control in order to drive a car with slow speed. On the other hand, there are approaches similar to the mentioned ALVINN and Nvidia concepts, that maps the road image directly into steering commands. OpenAI Universe makes experiments with computer games particularly easy, as it provides a complete environment for testing AI agents. Computer games are becoming complex enough to emulate the real world, therefore there are some active researches on data collection in virtual environments and evaluating models trained on this data in real traffic.

How IoT and machine learning can make our roads safer


Ben Dickson is a software engineer and the founder of TechTalks. The transportation industry is associated with high maintenance costs, disasters, accidents, injuries and loss of life. Hundreds of thousands of people across the world are losing their lives to car accidents and road disasters every year. According to the National Safety Council, 38,300 people were killed and 4.4 million injured on U.S. roads alone in 2015. The related costs -- including medical expenses, wage and productivity losses and property damage -- were estimated at $152 billion.