Learn More
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(More)
Recent advances in self-supervised learning have enabled very long-range visual detection of obstacles and pathways (to 100 meters or more). Unfortunately, the category and range of regions at such large distances come with a considerable amount of uncertainty. We present a mapping and planning system that accurately represents range and category(More)
Most vision-based approaches to mobile robotics suffer from the limitations imposed by stereo obstacle detection, which is short-range and prone to failure. We present a self-supervised learning process for long-range vision that is able to accurately classify complex terrain at distances up to the horizon, thus allowing superior strategic planning. The(More)
We describe a vision-based obstacle avoidance system for off-road mobile robots. The system is trained from end to end to map raw input images to steering angles. It is trained in supervised mode to predict the steering angles provided by a human driver during training runs collected in a wide variety of terrains, weather conditions, lighting conditions,(More)
Voicemail is a pervasive, but under-researched tool for workplace communication. Despite potential advantages of voicemail over email, current phone-based voicemail UIs are highly problematic for users. We present a novel, Web-based, voicemail interface, Jotmail. The design was based on data from several studies of voicemail tasks and user strategies. The(More)
We present a learning-based approach for long-range vision that is able to accurately classify complex terrain at distances up to the horizon, thus allowing high-level strategic planning. A deep belief network is trained with unsupervised data and a reconstruction criterion to extract features from an input image, and the features are used to train a(More)
Vision-based navigation and obstacle detection must be sophisticated in order to perform well in complicated and diverse terrain, but that complexity comes at the expense of increased system latency between image capture and actuator signals. Increased latency, or a longer control loop, degrades the reactivity of the robot. We present a nav-igational(More)
We present a solution to the problem of long-range obstacle/path recognition in autonomous robots. The system uses sparse traversability information from a stereo module to train a classifier online. The trained classifier can then accurately classify the entire scene. A distance-normalized image pyramid makes it possible to efficiently train a learning(More)
— Vehicle dynamics is typically handled by models whose parameters are found through system identification or manually computed from the vehicle's characteristics. While these methods provide accurate theoretical dynamical models, they may not take into account differences between individual vehicles, lack adaptability to new environments and may not handle(More)
The performance of vision-based navigation systems for off-road mobile robots depends crucially on the resolution of the camera, the sophistication of the visual processing, the latency between image and sensor capture to actuator control, and the period of the control loop. One particularly important design question is whether one should increase the(More)