scispace - formally typeset
Search or ask a question
Author

Mariusz Bojarski

Other affiliations: Nvidia
Bio: Mariusz Bojarski is an academic researcher from New York University. The author has contributed to research in topics: Wireless power transfer & Resonant inverter. The author has an hindex of 19, co-authored 45 publications receiving 3977 citations. Previous affiliations of Mariusz Bojarski include Nvidia.

Papers
More filters
Posted Content
TL;DR: A convolutional neural network is trained to map raw pixels from a single front-facing camera directly to steering commands and it is argued that this will eventually lead to better performance and smaller systems.
Abstract: We trained a convolutional neural network (CNN) to map raw pixels from a single front-facing camera directly to steering commands. This end-to-end approach proved surprisingly powerful. With minimum training data from humans the system learns to drive in traffic on local roads with or without lane markings and on highways. It also operates in areas with unclear visual guidance such as in parking lots and on unpaved roads. The system automatically learns internal representations of the necessary processing steps such as detecting useful road features with only the human steering angle as the training signal. We never explicitly trained it to detect, for example, the outline of roads. Compared to explicit decomposition of the problem, such as lane marking detection, path planning, and control, our end-to-end system optimizes all processing steps simultaneously. We argue that this will eventually lead to better performance and smaller systems. Better performance will result because the internal components self-optimize to maximize overall system performance, instead of optimizing human-selected intermediate criteria, e.g., lane detection. Such criteria understandably are selected for ease of human interpretation which doesn't automatically guarantee maximum system performance. Smaller networks are possible because the system learns to solve the problem with the minimal number of processing steps. We used an NVIDIA DevBox and Torch 7 for training and an NVIDIA DRIVE(TM) PX self-driving car computer also running Torch 7 for determining where to drive. The system operates at 30 frames per second (FPS).

3,379 citations

Posted Content
TL;DR: A method for determining which elements in the road image most influence PilotNet's steering decision is developed, and results show that PilotNet indeed learns to recognize relevant objects on the road.
Abstract: As part of a complete software stack for autonomous driving, NVIDIA has created a neural-network-based system, known as PilotNet, which outputs steering angles given images of the road ahead. PilotNet is trained using road images paired with the steering angles generated by a human driving a data-collection car. It derives the necessary domain knowledge by observing human drivers. This eliminates the need for human engineers to anticipate what is important in an image and foresee all the necessary rules for safe driving. Road tests demonstrated that PilotNet can successfully perform lane keeping in a wide variety of driving conditions, regardless of whether lane markings are present or not. The goal of the work described here is to explain what PilotNet learns and how it makes its decisions. To this end we developed a method for determining which elements in the road image most influence PilotNet's steering decision. Results show that PilotNet indeed learns to recognize relevant objects on the road. In addition to learning the obvious features such as lane markings, edges of roads, and other cars, PilotNet learns more subtle features that would be hard to anticipate and program by engineers, for example, bushes lining the edge of the road and atypical vehicle classes.

358 citations

Journal ArticleDOI
TL;DR: In this article, a phase shift control of a semibridgeless active rectifier (S-BAR) was investigated in order to utilize the SBAR in wireless energy transfer applications.
Abstract: A novel phase-shift control of a semibridgeless active rectifier (S-BAR) is investigated in order to utilize the S-BAR in wireless energy transfer applications. The standard receiver-side rectifier topology is developed by replacing rectifier lower diodes with synchronous switches controlled by a phase-shifted PWM signal. Theoretical and simulation results show that with the proposed control technique, the output quantities can be regulated without communication between the receiver and transmitter. To confirm the performance of the proposed converter and control, experimental results are provided using 8-, 15-, and 23-cm air gap coreless transformer which has dimension of 76 cm × 76 cm, with 120-V input and the output power range of 0 to 1kW with a maximum efficiency of 94.4%.

216 citations

Journal ArticleDOI
TL;DR: The Biot-Savart law is employed to calculate the magnetic field strength, which results in the proximity-effect resistance in single-layer litz-wire square solenoid coils without a magnetic core, and a strand-number coefficient is introduced to reflect the influence of the strand number inside the wire bundle on the proximity -effect resistance.
Abstract: In order to achieve the highest efficiency of wireless power transfer (WPT) systems, the quality factor of the resonant coil should be as high as possible. Due to the skin effect and the proximity effect, the coil resistance increases with the increase in the frequency. The highest quality factor exists for the optimal frequency together with the corresponding frequency-dependent inductor resistance. This paper employs the Biot–Savart law to calculate the magnetic field strength, which results in the proximity-effect resistance in single-layer litz-wire square solenoid coils without a magnetic core. A strand-number coefficient is introduced to reflect the influence of the strand number inside the wire bundle on the proximity-effect resistance. The coefficient is obtained through simple inductor resistance measurements for various numbers of litz-wire strands. The optimal frequency for the highest quality factor is derived based on the resistance evaluation. Several prototype coils were manufactured to verify the resistance analysis. Two $50\,\rm{cm}\times50\, {\rm cm}$ square coils were employed to construct a WPT prototype. The maximum dc–dc efficiency of this WPT was about 75% at 100-cm distance.

90 citations

Journal ArticleDOI
01 Jun 2017
TL;DR: In this paper, an inductively coupled multiphase resonant converter is presented for wireless electric vehicle charging applications as an alternative to the traditional frequency and phase shift control methods, a hybrid phase-frequency control strategy is implemented to improve the system efficiency.
Abstract: In this paper, an inductively coupled multiphase resonant converter is presented for wireless electric vehicle charging applications As an alternative to the traditional frequency and phase shift control methods, a hybrid phase-frequency control strategy is implemented to improve the system efficiency A theoretical analysis of the proposed system is carried out considering a wide battery state-of-charging range In order to confirm the proposed converter and control technique, a laboratory prototype wireless charger is designed using 8-in air-gap coreless transformer and rectifier The proposed control is compared with the conventional control methods for various load conditions at the different power levels In comparison results, the proposed hybrid control methodology demonstrates the efficiency improvements of 11% at the heaviest load condition and 57% at the lightest load condition

85 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: In this paper, the authors provide a classification of the main problems addressed in the literature with respect to the notion of explanation and the type of black box decision support systems, given a problem definition, a black box type, and a desired explanation, this survey should help the researcher to find the proposals more useful for his own work.
Abstract: In recent years, many accurate decision support systems have been constructed as black boxes, that is as systems that hide their internal logic to the user. This lack of explanation constitutes both a practical and an ethical issue. The literature reports many approaches aimed at overcoming this crucial weakness, sometimes at the cost of sacrificing accuracy for interpretability. The applications in which black box decision systems can be used are various, and each approach is typically developed to provide a solution for a specific problem and, as a consequence, it explicitly or implicitly delineates its own definition of interpretability and explanation. The aim of this article is to provide a classification of the main problems addressed in the literature with respect to the notion of explanation and the type of black box system. Given a problem definition, a black box type, and a desired explanation, this survey should help the researcher to find the proposals more useful for his own work. The proposed classification of approaches to open black box models should also be useful for putting the many research open questions in perspective.

2,805 citations

Book
01 Jan 2018

2,291 citations

Journal ArticleDOI
Amina Adadi1, Mohammed Berrada1
TL;DR: This survey provides an entry point for interested researchers and practitioners to learn key aspects of the young and rapidly growing body of research related to XAI, and review the existing approaches regarding the topic, discuss trends surrounding its sphere, and present major research trajectories.
Abstract: At the dawn of the fourth industrial revolution, we are witnessing a fast and widespread adoption of artificial intelligence (AI) in our daily life, which contributes to accelerating the shift towards a more algorithmic society. However, even with such unprecedented advancements, a key impediment to the use of AI-based systems is that they often lack transparency. Indeed, the black-box nature of these systems allows powerful predictions, but it cannot be directly explained. This issue has triggered a new debate on explainable AI (XAI). A research field holds substantial promise for improving trust and transparency of AI-based systems. It is recognized as the sine qua non for AI to continue making steady progress without disruption. This survey provides an entry point for interested researchers and practitioners to learn key aspects of the young and rapidly growing body of research related to XAI. Through the lens of the literature, we review the existing approaches regarding the topic, discuss trends surrounding its sphere, and present major research trajectories.

2,258 citations

Journal ArticleDOI
TL;DR: Eyeriss as mentioned in this paper is an accelerator for state-of-the-art deep convolutional neural networks (CNNs) that optimizes for the energy efficiency of the entire system, including the accelerator chip and off-chip DRAM, by reconfiguring the architecture.
Abstract: Eyeriss is an accelerator for state-of-the-art deep convolutional neural networks (CNNs). It optimizes for the energy efficiency of the entire system, including the accelerator chip and off-chip DRAM, for various CNN shapes by reconfiguring the architecture. CNNs are widely used in modern AI systems but also bring challenges on throughput and energy efficiency to the underlying hardware. This is because its computation requires a large amount of data, creating significant data movement from on-chip and off-chip that is more energy-consuming than computation. Minimizing data movement energy cost for any CNN shape, therefore, is the key to high throughput and energy efficiency. Eyeriss achieves these goals by using a proposed processing dataflow, called row stationary (RS), on a spatial architecture with 168 processing elements. RS dataflow reconfigures the computation mapping of a given shape, which optimizes energy efficiency by maximally reusing data locally to reduce expensive data movement, such as DRAM accesses. Compression and data gating are also applied to further improve energy efficiency. Eyeriss processes the convolutional layers at 35 frames/s and 0.0029 DRAM access/multiply and accumulation (MAC) for AlexNet at 278 mW (batch size $N = 4$ ), and 0.7 frames/s and 0.0035 DRAM access/MAC for VGG-16 at 236 mW ( $N = 3$ ).

2,165 citations

01 Sep 2010

2,148 citations