arXiv subjects

Lex Fridman

Publications and source records attributed to Lex Fridman.

At least 19 recordsLinked to original sources

arXiv2023

CLERA: A Unified Model for Joint Cognitive Load and Eye Region Analysis in the Wild

Non-intrusive, real-time analysis of the dynamics of the eye region allows us to monitor humans' visual attention allocation and estimate their mental state during the performance of real-world tasks, which can potentially benefit a wide range of human-computer interaction (HCI) applications. While commercial eye-tracking devices have been frequently employed, the difficulty of customizing these devices places unnecessary constraints on the exploration of more efficient, end-to-end models of eye dynamics. In this work, we propose CLERA, a unified model for Cognitive Load and Eye Region Analysis, which achieves precise keypoint detection and spatiotemporal tracking in a joint-learning framework. Our method demonstrates significant efficiency and outperforms prior work on tasks including cognitive load estimation, eye landmark detection, and blink estimation. We also introduce a large-scale dataset of 30k human faces with joint pupil, eye-openness, and landmark annotation, which aims to support future HCI research on human factors and eye-related analysis.

cs.HC↗

arXiv2019

Object as Distribution

Object detection is a critical part of visual scene understanding. The representation of the object in the detection task has important implications on the efficiency and feasibility of annotation, robustness to occlusion, pose, lighting, and other visual sources of semantic uncertainty, and effectiveness in real-world applications (e.g., autonomous driving). Popular object representations include 2D and 3D bounding boxes, polygons, splines, pixels, and voxels. Each have their strengths and weakness. In this work, we propose a new representation of objects based on the bivariate normal distribution. This distribution-based representation has the benefit of robust detection of highly-overlapping objects and the potential for improved downstream tracking and instance segmentation tasks due to the statistical representation of object edges. We provide qualitative evaluation of this representation for the object detection task and quantitative evaluation of its use in a baseline algorithm for the instance segmentation task.

cs.CV↗

arXiv2019

Eye Contact Between Pedestrians and Drivers

When asked, a majority of people believe that, as pedestrians, they make eye contact with the driver of an approaching vehicle when making their crossing decisions. This work presents evidence that this widely held belief is false. We do so by showing that, in majority of cases where conflict is possible, pedestrians begin crossing long before they are able to see the driver through the windshield. In other words, we are able to circumvent the very difficult question of whether pedestrians choose to make eye contact with drivers, by showing that whether they think they do or not, they can't. Specifically, we show that over 90\% of people in representative lighting conditions cannot determine the gaze of the driver at 15m and see the driver at all at 30m. This means that, for example, that given the common city speed limit of 25mph, more than 99% of pedestrians would have begun crossing before being able to see either the driver or the driver's gaze. In other words, from the perspective of the pedestrian, in most situations involving an approaching vehicle, the crossing decision is made by the pedestrian solely based on the kinematics of the vehicle without needing to determine that eye contact was made by explicitly detecting the eyes of the driver.

cs.HC↗

arXiv2019

Dynamics of Pedestrian Crossing Decisions Based on Vehicle Trajectories in Large-Scale Simulated and Real-World Data

Humans, as both pedestrians and drivers, generally skillfully navigate traffic intersections. Despite the uncertainty, danger, and the non-verbal nature of communication commonly found in these interactions, there are surprisingly few collisions considering the total number of interactions. As the role of automation technology in vehicles grows, it becomes increasingly critical to understand the relationship between pedestrian and driver behavior: how pedestrians perceive the actions of a vehicle/driver and how pedestrians make crossing decisions. The relationship between time-to-arrival (TTA) and pedestrian gap acceptance (i.e., whether a pedestrian chooses to cross under a given window of time to cross) has been extensively investigated. However, the dynamic nature of vehicle trajectories in the context of non-verbal communication has not been systematically explored. Our work provides evidence that trajectory dynamics, such as changes in TTA, can be powerful signals in the non-verbal communication between drivers and pedestrians. Moreover, we investigate these effects in both simulated and real-world datasets, both larger than have previously been considered in literature to the best of our knowledge.

cs.HC↗

arXiv2019

Hacking Nonverbal Communication Between Pedestrians and Vehicles in Virtual Reality

We use an immersive virtual reality environment to explore the intricate social cues that underlie non-verbal communication involved in a pedestrian's crossing decision. We "hack" non-verbal communication between pedestrian and vehicle by engineering a set of 15 vehicle trajectories, some of which follow social conventions and some that break them. By subverting social expectations of vehicle behavior we show that pedestrians may use vehicle kinematics to infer social intentions and not merely as the state of a moving object. We investigate human behavior in this virtual world by conducting a study of 22 subjects, with each subject experiencing and responding to each of the trajectories by moving their body, legs, arms, and head in both the physical and the virtual world. Both quantitative and qualitative responses are collected and analyzed, showing that, in fact, social cues can be engineered through vehicle trajectory manipulation. In addition, we demonstrate that immersive virtual worlds which allow the pedestrian to move around freely, provide a powerful way to understand both the mechanisms of human perception and the social signaling involved in pedestrian-vehicle interaction.

cs.HC↗

arXiv2019

Value of Temporal Dynamics Information in Driving Scene Segmentation

Semantic scene segmentation has primarily been addressed by forming representations of single images both with supervised and unsupervised methods. The problem of semantic segmentation in dynamic scenes has begun to recently receive attention with video object segmentation approaches. What is not known is how much extra information the temporal dynamics of the visual scene carries that is complimentary to the information available in the individual frames of the video. There is evidence that the human visual system can effectively perceive the scene from temporal dynamics information of the scene's changing visual characteristics without relying on the visual characteristics of individual snapshots themselves. Our work takes steps to explore whether machine perception can exhibit similar properties by combining appearance-based representations and temporal dynamics representations in a joint-learning problem that reveals the contribution of each toward successful dynamic scene segmentation. Additionally, we provide the MIT Driving Scene Segmentation dataset, which is a large-scale full driving scene segmentation dataset, densely annotated for every pixel and every one of 5,000 video frames. This dataset is intended to help further the exploration of the value of temporal dynamics information for semantic segmentation in video.

cs.CV↗

arXiv2018

Human-Centered Autonomous Vehicle Systems: Principles of Effective Shared Autonomy

Building effective, enjoyable, and safe autonomous vehicles is a lot harder than has historically been considered. The reason is that, simply put, an autonomous vehicle must interact with human beings. This interaction is not a robotics problem nor a machine learning problem nor a psychology problem nor an economics problem nor a policy problem. It is all of these problems put into one. It challenges our assumptions about the limitations of human beings at their worst and the capabilities of artificial intelligence systems at their best. This work proposes a set of principles for designing and building autonomous vehicles in a human-centered way that does not run away from the complexity of human nature but instead embraces it. We describe our development of the Human-Centered Autonomous Vehicle (HCAV) as an illustrative case study of implementing these principles in practice.

cs.AI↗

arXiv2018

Designing Toward Minimalism in Vehicle HMI

We propose that safe, beautiful, fulfilling vehicle HMI design must start from a rigorous consideration of minimalist design. Modern vehicles are changing from mechanical machines to mobile computing devices, similar to the change from landline phones to smartphones. We propose the approach of "designing toward minimalism", where we ask "why?" rather than "why not?" in choosing what information to display to the driver. We demonstrate this approach on an HMI case study of displaying vehicle speed. We first show that vehicle speed is what 87.6% of people ask for. We then show, through an online study with 1,038 subjects and 22,950 videos, that humans can estimate ego-vehicle speed very well, especially at lower speeds. Thus, despite believing that we need this information, we may not. In this way, we demonstrate a systematic approach of questioning the fundamental assumptions of what information is essential for vehicle HMI.

cs.HC↗

arXiv2018

A Machine Learning Approach for Power Allocation in HetNets Considering QoS

There is an increase in usage of smaller cells or femtocells to improve performance and coverage of next-generation heterogeneous wireless networks (HetNets). However, the interference caused by femtocells to neighboring cells is a limiting performance factor in dense HetNets. This interference is being managed via distributed resource allocation methods. However, as the density of the network increases so does the complexity of such resource allocation methods. Yet, unplanned deployment of femtocells requires an adaptable and self-organizing algorithm to make HetNets viable. As such, we propose to use a machine learning approach based on Q-learning to solve the resource allocation problem in such complex networks. By defining each base station as an agent, a cellular network is modelled as a multi-agent network. Subsequently, cooperative Q-learning can be applied as an efficient approach to manage the resources of a multi-agent network. Furthermore, the proposed approach considers the quality of service (QoS) for each user and fairness in the network. In comparison with prior work, the proposed approach can bring more than a four-fold increase in the number of supported femtocells while using cooperative Q-learning to reduce resource allocation overhead.

cs.IT↗

arXiv2018

DeepTraffic: Crowdsourced Hyperparameter Tuning of Deep Reinforcement Learning Systems for Multi-Agent Dense Traffic Navigation

We present a traffic simulation named DeepTraffic where the planning systems for a subset of the vehicles are handled by a neural network as part of a model-free, off-policy reinforcement learning process. The primary goal of DeepTraffic is to make the hands-on study of deep reinforcement learning accessible to thousands of students, educators, and researchers in order to inspire and fuel the exploration and evaluation of deep Q-learning network variants and hyperparameter configurations through large-scale, open competition. This paper investigates the crowd-sourced hyperparameter tuning of the policy network that resulted from the first iteration of the DeepTraffic competition where thousands of participants actively searched through the hyperparameter space.

cs.NE↗

arXiv2017

MIT Advanced Vehicle Technology Study: Large-Scale Naturalistic Driving Study of Driver Behavior and Interaction with Automation

For the foreseeble future, human beings will likely remain an integral part of the driving task, monitoring the AI system as it performs anywhere from just over 0% to just under 100% of the driving. The governing objectives of the MIT Autonomous Vehicle Technology (MIT-AVT) study are to (1) undertake large-scale real-world driving data collection that includes high-definition video to fuel the development of deep learning based internal and external perception systems, (2) gain a holistic understanding of how human beings interact with vehicle automation technology by integrating video data with vehicle state data, driver characteristics, mental models, and self-reported experiences with technology, and (3) identify how technology and other factors related to automation adoption and use can be improved in ways that save lives. In pursuing these objectives, we have instrumented 23 Tesla Model S and Model X vehicles, 2 Volvo S90 vehicles, 2 Range Rover Evoque, and 2 Cadillac CT6 vehicles for both long-term (over a year per driver) and medium term (one month per driver) naturalistic driving data collection. Furthermore, we are continually developing new methods for analysis of the massive-scale dataset collected from the instrumented vehicle fleet. The recorded data streams include IMU, GPS, CAN messages, and high-definition video streams of the driver face, the driver cabin, the forward roadway, and the instrument cluster (on select vehicles). The study is on-going and growing. To date, we have 122 participants, 15,610 days of participation, 511,638 miles, and 7.1 billion video frames. This paper presents the design of the study, the data collection hardware, the processing of the data, and the computer vision algorithms currently being used to extract actionable knowledge from the data.

cs.CY↗

arXiv2017

Arguing Machines: Human Supervision of Black Box AI Systems That Make Life-Critical Decisions

We consider the paradigm of a black box AI system that makes life-critical decisions. We propose an "arguing machines" framework that pairs the primary AI system with a secondary one that is independently trained to perform the same task. We show that disagreement between the two systems, without any knowledge of underlying system design or operation, is sufficient to arbitrarily improve the accuracy of the overall decision pipeline given human supervision over disagreements. We demonstrate this system in two applications: (1) an illustrative example of image classification and (2) on large-scale real-world semi-autonomous driving data. For the first application, we apply this framework to image classification achieving a reduction from 8.0% to 2.8% top-5 error on ImageNet. For the second application, we apply this framework to Tesla Autopilot and demonstrate the ability to predict 90.4% of system disengagements that were labeled by human annotators as challenging and needing human supervision.

cs.AI↗

arXiv2017

To Walk or Not to Walk: Crowdsourced Assessment of External Vehicle-to-Pedestrian Displays

Researchers, technology reviewers, and governmental agencies have expressed concern that automation may necessitate the introduction of added displays to indicate vehicle intent in vehicle-to-pedestrian interactions. An automated online methodology for obtaining communication intent perceptions for 30 external vehicle-to-pedestrian display concepts was implemented and tested using Amazon Mechanic Turk. Data from 200 qualified participants was quickly obtained and processed. In addition to producing a useful early-stage evaluation of these specific design concepts, the test demonstrated that the methodology is scalable so that a large number of design elements or minor variations can be assessed through a series of runs even on much larger samples in a matter of hours. Using this approach, designers should be able to refine concepts both more quickly and in more depth than available development resources typically allow. Some concerns and questions about common assumptions related to the implementation of vehicle-to-pedestrian displays are posed.

cs.HC↗

arXiv2017

SideEye: A Generative Neural Network Based Simulator of Human Peripheral Vision

Foveal vision makes up less than 1% of the visual field. The other 99% is peripheral vision. Precisely what human beings see in the periphery is both obvious and mysterious in that we see it with our own eyes but can't visualize what we see, except in controlled lab experiments. Degradation of information in the periphery is far more complex than what might be mimicked with a radial blur. Rather, behaviorally-validated models hypothesize that peripheral vision measures a large number of local texture statistics in pooling regions that overlap and grow with eccentricity. In this work, we develop a new method for peripheral vision simulation by training a generative neural network on a behaviorally-validated full-field synthesis model. By achieving a 21,000 fold reduction in running time, our approach is the first to combine realism and speed of peripheral vision simulation to a degree that provides a whole new way to approach visual design: through peripheral visualization.

cs.NE↗

arXiv2016

Semi-Automated Annotation of Discrete States in Large Video Datasets

We propose a framework for semi-automated annotation of video frames where the video is of an object that at any point in time can be labeled as being in one of a finite number of discrete states. A Hidden Markov Model (HMM) is used to model (1) the behavior of the underlying object and (2) the noisy observation of its state through an image processing algorithm. The key insight of this approach is that the annotation of frame-by-frame video can be reduced from a problem of labeling every single image to a problem of detecting a transition between states of the underlying objected being recording on video. The performance of the framework is evaluated on a driver gaze classification dataset composed of 16,000,000 images that were fully annotated over 6,000 hours of direct manual annotation labor. On this dataset, we achieve a 13x reduction in manual annotation for an average accuracy of 99.1% and a 84x reduction for an average accuracy of 91.2%.

cs.CV↗

arXiv2016

What Can Be Predicted from Six Seconds of Driver Glances?

We consider a large dataset of real-world, on-road driving from a 100-car naturalistic study to explore the predictive power of driver glances and, specifically, to answer the following question: what can be predicted about the state of the driver and the state of the driving environment from a 6-second sequence of macro-glances? The context-based nature of such glances allows for application of supervised learning to the problem of vision-based gaze estimation, making it robust, accurate, and reliable in messy, real-world conditions. So, it's valuable to ask whether such macro-glances can be used to infer behavioral, environmental, and demographic variables? We analyze 27 binary classification problems based on these variables. The takeaway is that glance can be used as part of a multi-sensor real-time system to predict radio-tuning, fatigue state, failure to signal, talking, and several environment variables.

cs.CV↗

arXiv2016

Investigating Drivers' Head and Glance Correspondence

The relationship between a driver's glance pattern and corresponding head rotation is highly complex due to its nonlinear dependence on the individual, task, and driving context. This study explores the ability of head pose to serve as an estimator for driver gaze by connecting head rotation data with manually coded gaze region data using both a statistical analysis approach and a predictive (i.e., machine learning) approach. For the latter, classification accuracy increased as visual angles between two glance locations increased. In other words, the greater the shift in gaze, the higher the accuracy of classification. This is an intuitive but important concept that we make explicit through our analysis. The highest accuracy achieved was 83% using the method of Hidden Markov Models (HMM) for the binary gaze classification problem of (1) the forward roadway versus (2) the center stack. Results suggest that although there are individual differences in head-glance correspondence while driving, classifier models based on head-rotation data may be robust to these differences and therefore can serve as reasonable estimators for glance location. The results suggest that driver head pose can be used as a surrogate for eye gaze in several key conditions including the identification of high-eccentricity glances. Inexpensive driver head pose tracking may be a key element in detection systems developed to mitigate driver distraction and inattention.

cs.OH↗

arXiv2015

On the joint impact of bias and power control on downlink spectral efficiency in cellular networks

Cell biasing and downlink transmit power are two controls that may be used to improve the spectral efficiency of cellular networks. With cell biasing, each mobile user associates with the base station offering, say, the highest biased signal to interference plus noise ratio. Biasing affects the cell association decisions of mobile users, but not the received instantaneous downlink transmission rates. Adjusting the collection of downlink transmission powers can likewise affect the cell associations, but in contrast with biasing, it also directly affects the instantaneous rates. This paper investigates the joint use of both cell biasing and transmission power control and their (individual and joint) effects on the statistical properties of the collection of per-user spectral efficiencies. Our analytical results and numerical investigations demonstrate in some cases a significant performance improvement in the Pareto efficient frontiers of both a mean-variance and throughput-fairness tradeoff from using both bias and power controls over using either control alone.

cs.IT↗