Using deep reinforcement learning, we train control policies for autonomous vehicles leading a platoon of vehicles onto a roundabout. Using Flow, a library for deep reinforcement learning in micro-simulators, we train two policies, one policy with noise injected into the state and action space and one without any injected noise. In simulation, the autonomous vehicle learns an emergent metering behavior for both policies in which it slows to allow for smoother merging. We then directly transfer this policy without any tuning to the University of Delaware Scaled Smart City (UDSSC), a 1:25 scale testbed for connected and automated vehicles. We characterize the performance of both policies on the scaled city. We show that the noise-free policy winds up crashing and only occasionally metering. However, the noise-injected policy consistently performs the metering behavior and remains collision-free, suggesting that the noise helps with the zero-shot policy transfer. Additionally, the transferred, noise-injected policy leads to a 5% reduction of average travel time and a reduction of 22% in maximum travel time in the UDSSC. Videos of the controllers can be found at https://sites.google.com/view/iccps-policy-transfer.
Is it Safe to Drive? Abstract--With recent advances in learning algorithms and hardware development, autonomous cars have shown promise when operating in structured environments under good driving conditions. However, for complex, cluttered and unseen environments withhigh uncertainty, autonomous driving systems still frequently demonstrate erroneous or unexpected behaviors, that could lead to catastrophic outcomes. Autonomous vehicles should ideally adapt to driving conditions; while this can be achieved through multiple routes, it would be beneficial as a first step to be able to characterize Driveability in some quantified form. To this end, this paper aims to create a framework for investigating different factors that can impact driveability. Also, one of the main mechanisms to adapt autonomous driving systems to any driving condition is to be able to learn and generalize from representative scenarios. The machine learning algorithms that currently do so learn predominantly in a supervised manner and consequently need sufficient data for robust and efficient learning. Specifically,we categorize the datasets according to use cases, and highlight the datasets that capture complicated and hazardous driving conditions which can be better used for training robust driving models. Furthermore, by discussions of what driving scenarios are not covered by existing public datasets and what driveability factors need more investigation and data acquisition, this paper aims to encourage both targeted dataset collection and the proposal of novel driveability metrics that enhance the robustness of autonomous cars in adverse environments. I. INTRODUCTION Despite testing autonomous cars in highly controlled settings, thesecars still occasionally fail in making correct decisions, often with catastrophic results According to the accident records, the failures are most likely to happen in complex or unseen driving environments. The fact remains that while autonomous cars can operate well in controlled or structured environments such as highways, they are still far from reliable when operating in cluttered, unstructured or unseen environments . These apply to autonomous vehicles in general. Thesetwo different application fields also suggest that driveability could be quantified in different forms, either as a single metric or a composition of metrics. For example, with ADAS and current Level 2 or 3 autonomy, a scene can be simply defined as driveable if the car can operate safely in autonomous mode. When a non-driveable scene is detected, the autonomous car can hand over control to the human driver in a timely manner .
Self-driving cars are being developed by several major technology companies and carmakers. When a driver slams on the brakes to avoid hitting a pedestrian crossing the road illegally, she is making a moral decision that shifts risk from the pedestrian to the people in the car. Self-driving cars might soon have to make such ethical judgments on their own -- but settling on a universal moral code for the vehicles could be a thorny task, suggests a survey of 2.3 million people from around the world. The largest ever survey of machine ethics1, published today in Nature, finds that many of the moral principles that guide a driver's decisions vary by country. For example, in a scenario in which some combination of pedestrians and passengers will die in a collision, people from relatively prosperous countries with strong institutions were less likely to spare a pedestrian who stepped into traffic illegally.
Those expectations are now hitting speed bumps, according to interviews with eight current and former GM and Cruise employees and executives, along with nine autonomous vehicle technology experts familiar with Cruise. These sources say that some unexpected technical challenges - including the difficulty that Cruise cars have identifying whether objects are in motion - mean putting GM's driverless cars on the road in a large scale way in 2019 is looking highly unlikely.
Unmanned Aerial Vehicles (UAVs) have recently rapidly grown to facilitate a wide range of innovative applications that can fundamentally change the way cyber-physical systems (CPSs) are designed. CPSs are a modern generation of systems with synergic cooperation between computational and physical potentials that can interact with humans through several new mechanisms. The main advantages of using UAVs in CPS application is their exceptional features, including their mobility, dynamism, effortless deployment, adaptive altitude, agility, adjustability, and effective appraisal of real-world functions anytime and anywhere. Furthermore, from the technology perspective, UAVs are predicted to be a vital element of the development of advanced CPSs. Therefore, in this survey, we aim to pinpoint the most fundamental and important design challenges of multi-UAV systems for CPS applications. We highlight key and versatile aspects that span the coverage and tracking of targets and infrastructure objects, energy-efficient navigation, and image analysis using machine learning for fine-grained CPS applications. Key prototypes and testbeds are also investigated to show how these practical technologies can facilitate CPS applications. We present and propose state-of-the-art algorithms to address design challenges with both quantitative and qualitative methods and map these challenges with important CPS applications to draw insightful conclusions on the challenges of each application. Finally, we summarize potential new directions and ideas that could shape future research in these areas.
Example of a recorded highway including bounding boxes and labels of detected vehicles. The color of the bounding boxes indicates the class of the detected object (car: yellow, truck: green). Every vehicle is assigned a unique id for tracking and its speed is estimated over time. Abstract-- Scenario-based testing for the safety validation of highly automated vehicles is a promising approach that is being examined in research and industry. This approach heavily relies on data from real-world scenarios to derive the necessary scenario information for testing. Measurement data should be collected at a reasonable effort, contain naturalistic behavior of road users and include all data relevant for a description of the identified scenarios in sufficient quality. However, the current measurement methods fail to meet at least one of the requirements. Thus, we propose a novel method to measure data from an aerial perspective for scenario-based validation fulfilling the mentioned requirements. Furthermore, we provide a large-scale naturalistic vehicle trajectory dataset from German highways called highD. We evaluate the data in terms of quantity, variety and contained scenarios. Our dataset consists of 16.5 hours of measurements from six locations with 110 000 vehicles, a total driven distance of 45 000 km and 5600 recorded complete lane changes. A technical proof of concept for highly automated driving (HAD) has already been shown in many demonstrations and test drives.
Electric drones booked through smartphones pick people up from office rooftops, shortening travel time by hours, reducing the need for parking and clearing smog from the air. This vision of the future is driving the government's "flying car" project. Major carrier All Nippon Airways, electronics company NEC Corp. and more than a dozen other companies and academic experts hope to have a road map for the plan ready by the year's end. "This is such a totally new sector Japan has a good chance for not falling behind," said Fumiaki Ebihara, the government official in charge of the project. For now, nobody believes people are going to be zipping around in flying cars any time soon.
Chinese companies are "aggressively investing" in artificial intelligence (AI) applications and show more thirst for talent, a joint study by Massachusetts Institute of Technology (MIT) and Boston Consulting Group (BCG) shows, at a time when the race for AI superiority is in the spotlight around the world. The conclusion – based on a survey of over 3,000 participants in 126 countries and 300 executives from China – shines a light on China's ambitions in AI, which is seen as a major driver of the new economy, and the perceived competitive threat the country poses to other big economies. "China's rapid rise in AI has been a wake-up call for nations, industries and corporate executives globally," says the report, which was released on Tuesday and titled Artificial Intelligence in Business Gets Real. "Indeed, many recent national programmes to advance the development of AI refer to China as a competitive threat." Betting big on the core technology behind an array of cutting-edge applications from autonomous driving to facial recognition, China's State Council last July laid out a three-step road map to AI supremacy.
Autonomous driving presents one of the largest problems that the robotics and artificial intelligence communities are facing at the moment, both in terms of difficulty and potential societal impact. Self-driving vehicles (SDVs) are expected to prevent road accidents and save millions of lives while improving the livelihood and life quality of many more. However, despite large interest and a number of industry players working in the autonomous domain, there is still more to be done in order to develop a system capable of operating at a level comparable to best human drivers. One reason for this is high uncertainty of traffic behavior and large number of situations that an SDV may encounter on the roads, making it very difficult to create a fully generalizable system. To ensure safe and efficient operations, an autonomous vehicle is required to account for this uncertainty and to anticipate a multitude of possible behaviors of traffic actors in its surrounding. In this work, we address this critical problem and present a method to predict multiple possible trajectories of actors while also estimating their probabilities. The method encodes each actor's surrounding context into a raster image, used as input by deep convolutional networks to automatically derive relevant features for the task. Following extensive offline evaluation and comparison to state-of-the-art baselines, as well as closed course tests, the method was successfully deployed to a fleet of SDVs.
The joint availability of computational power and huge datasets has considerably changed the landscape of Artificial Intelligence. In many fields, applications (self-driving cars, cybersecurity, e-health…) that seemed out of reach in the past are now closer to becoming a reality. Recent advances in Machine Learning, the key component of AI, show the growing maturity of algorithms that are now able to handle an increasing number of new tasks. However, simple adversarial attacks can still easily defeat a learning algorithm and the potentially massive deployment of AI tools in various environments raises many new concerns. Additionally to scalability and versatility of algorithms, awareness of drifting or fake data, privacy, interpretability, accountability are now all features that a learning and decision system should take into account.