Neural Networks

NVIDIAVoice: AI Is Enabling Our Need For Speed And Safety In Racecar Driving


The racing industry is on the fast track to driverless racecars, thanks to AI. At the center of this evolution is Roborace, the world's first autonomous racing competition. Conceived by renowned car designer Daniel Simon -- a former Bugatti designer who's gone on to create various cars for Hollywood -- the "Robocar" is designed, developed, and built by the Roborace organization. Teams compete by writing the software and developing deep neural networks that consume the sensor data to see, think, and act. The cars -- which are 4.8-meters-long -- can reach speeds of over 300 kilometers per hour.

NVIDIAVoice: Building The AI Architecture To Train, Simulate And Test AI Self-Driving Cars

Forbes Technology

Developing an autonomous vehicle requires a massive amount of data. Before any AV can safely navigate on the road, engineers must first train the artificial intelligence (AI) algorithms that enable the car to drive itself. Deep learning, a form of AI, is used to perceive the environment surrounding the car and to make driving decisions with superhuman levels of performance and precision. This is an enormous big data challenge. A single test vehicle can generate petabytes of data a year.

A Study of EV BMS Cyber Security Based on Neural Network SOC Prediction Machine Learning

Recent changes to greenhouse gas emission policies are catalyzing the electric vehicle (EV) market making it readily accessible to consumers. While there are challenges that arise with dense deployment of EVs, one of the major future concerns is cyber security threat. In this paper, cyber security threats in the form of tampering with EV battery's State of Charge (SOC) was explored. A Back Propagation (BP) Neural Network (NN) was trained and tested based on experimental data to estimate SOC of battery under normal operation and cyber-attack scenarios. NeuralWare software was used to run scenarios. Different statistic metrics of the predicted values were compared against the actual values of the specific battery tested to measure the stability and accuracy of the proposed BP network under different operating conditions. The results showed that BP NN was able to capture and detect the false entries due to a cyber-attack on its network.

Foresee: Attentive Future Projections of Chaotic Road Environments with Online Training Machine Learning

In this paper, we train a recurrent neural network to learn dynamics of a chaotic road environment and to project the future of the environment on an image. Future projection can be used to anticipate an unseen environment for example, in autonomous driving. Road environment is highly dynamic and complex due to the interaction among traffic participants such as vehicles and pedestrians. Even in this complex environment, a human driver is efficacious to safely drive on chaotic roads irrespective of the number of traffic participants. The proliferation of deep learning research has shown the efficacy of neural networks in learning this human behavior. In the same direction, we investigate recurrent neural networks to understand the chaotic road environment which is shared by pedestrians, vehicles (cars, trucks, bicycles etc.), and sometimes animals as well. We propose \emph{Foresee}, a unidirectional gated recurrent units (GRUs) network with attention to project future of the environment in the form of images. We have collected several videos on Delhi roads consisting of various traffic participants, background and infrastructure differences (like 3D pedestrian crossing) at various times on various days. We train \emph{Foresee} in an unsupervised way and we use online training to project frames up to $0.5$ seconds in advance. We show that our proposed model performs better than state of the art methods (prednet and Enc. Dec. LSTM) and finally, we show that our trained model generalizes to a public dataset for future projections.

Self-driving cars are NOT safe 'while in the wild', says the co-founder of Google's DeepMind

Daily Mail

The co-founder of Google's DeepMind has slammed self-driving cars for not being safe enough, saying current early tests on public roads are irresponsible. Demis Hassabis has urged developers to be cautious with the new technology, saying it is difficult to prove systems are safe before putting them on public roads. The issue of AI in self-driving cars has flared up this year following the death of a women hit but a self-driving Uber in March. The accident was the first time a pedestrian was killed on a public road by an autonomous car, which had previously been praised as the safer alternative to a traditional car. Speaking at the Royal Society in London, Dr Hassabis said current driverless car programmes could be putting people's lives in danger.

Vehicle Detection and Tracking using Machine Learning and HOG


I am into my first term of Udacity's Self Driving Car Nanodegree and I want to share my experience regarding the final project of Term 1 i.e. The complete code can be found here. The basic objective of this project is to apply the concepts of HOG and Machine Learning to detect a Vehicle from a dashboard video. Sure, the Deep Learning implementations like YOLO and SSD that utilize convolutional neural network stand out for this purpose but when you are a beginner in this field, its better to start with the classical approach. The most important thing for any machine learning problem is the labelled data set and here we need to have two sets of data: Vehicle and Non Vehicle Images.

Artificial Intelligence: Science fiction to science fact - Connected Magazine


Artificial intelligence is quickly growing in importance in the'smart building' sector. Paul Skelton looks at the road ahead for a complex technology. When Mark Chung received an unexpectedly high $500 monthly electricity bill, he turned to his utility for help and answers. However, despite'smart' meters being installed in his home, they were no help. So Mark – an electrical engineer trained at Stanford University – took matters into his own hands.

Driving maneuvers prediction based on cognition-driven and data-driven method Artificial Intelligence

Advanced Driver Assistance Systems (ADAS) improve driving safety significantly. They alert drivers from unsafe traffic conditions when a dangerous maneuver appears. Traditional methods to predict driving maneuvers are mostly based on data-driven models alone. However, existing methods to understand the driver's intention remain an ongoing challenge due to a lack of intersection of human cognition and data analysis. To overcome this challenge, we propose a novel method that combines both the cognition-driven model and the data-driven model. We introduce a model named Cognitive Fusion-RNN (CF-RNN) which fuses the data inside the vehicle and the data outside the vehicle in a cognitive way. The CF-RNN model consists of two Long Short-Term Memory (LSTM) branches regulated by human reaction time. Experiments on the Brain4Cars benchmark dataset demonstrate that the proposed method outperforms previous methods and achieves state-of-the-art performance.

Robust Deep Reinforcement Learning for Security and Safety in Autonomous Vehicle Systems Artificial Intelligence

To operate effectively in tomorrow's smart cities, autonomous vehicles (AVs) must rely on intra-vehicle sensors such as camera and radar as well as inter-vehicle communication. Such dependence on sensors and communication links exposes AVs to cyber-physical (CP) attacks by adversaries that seek to take control of the AVs by manipulating their data. Thus, to ensure safe and optimal AV dynamics control, the data processing functions at AVs must be robust to such CP attacks. To this end, in this paper, the state estimation process for monitoring AV dynamics, in presence of CP attacks, is analyzed and a novel adversarial deep reinforcement learning (RL) algorithm is proposed to maximize the robustness of AV dynamics control to CP attacks. The attacker's action and the AV's reaction to CP attacks are studied in a game-theoretic framework. In the formulated game, the attacker seeks to inject faulty data to AV sensor readings so as to manipulate the inter-vehicle optimal safe spacing and potentially increase the risk of AV accidents or reduce the vehicle flow on the roads. Meanwhile, the AV, acting as a defender, seeks to minimize the deviations of spacing so as to ensure robustness to the attacker's actions. Since the AV has no information about the attacker's action and due to the infinite possibilities for data value manipulations, the outcome of the players' past interactions are fed to long-short term memory (LSTM) blocks. Each player's LSTM block learns the expected spacing deviation resulting from its own action and feeds it to its RL algorithm. Then, the the attacker's RL algorithm chooses the action which maximizes the spacing deviation, while the AV's RL algorithm tries to find the optimal action that minimizes such deviation.

Ultra Low Power Deep-Learning-powered Autonomous Nano Drones Artificial Intelligence

Flying in dynamic, urban, highly-populated environments represents an open problem in robotics. State-of-the-art (SoA) autonomous Unmanned Aerial Vehicles (UAVs) employ advanced computer vision techniques based on computationally expensive algorithms, such as Simultaneous Localization and Mapping (SLAM) or Convolutional Neural Networks (CNNs) to navigate in such environments. In the Internet-of-Things (IoT) era, nano-size UAVs capable of autonomous navigation would be extremely desirable as self-aware mobile IoT nodes. However, autonomous flight is considered unaffordable in the context of nano-scale UAVs, where the ultra-constrained power envelopes of tiny rotor-crafts limit the on-board computational capabilities to low-power microcontrollers. In this work, we present the first vertically integrated system for fully autonomous deep neural network-based navigation on nano-size UAVs. Our system is based on GAP8, a novel parallel ultra-low-power computing platform, and deployed on a 27 g commercial, open-source CrazyFlie 2.0 nano-quadrotor. We discuss a methodology and software mapping tools that enable the SoA CNN presented in [1] to be fully executed on-board within a strict 12 fps real-time constraint with no compromise in terms of flight results, while all processing is done with only 94 mW on average - 1% of the power envelope of the deployed nano-aircraft.