Predicting the motion of a driver's vehicle is crucial for advanced driving systems, enabling detection of potential risks towards shared control between the driver and automation systems. In this paper, we propose a variational neural network approach that predicts future driver trajectory distributions for the vehicle based on multiple sensors. Our predictor generates both a conditional variational distribution of future trajectories, as well as a confidence estimate for different time horizons. Our approach allows us to handle inherently uncertain situations, and reason about information gain from each input, as well as combine our model with additional predictors, creating a mixture of experts. We show how to augment the variational predictor with a physics-based predictor, and based on their confidence estimations, improve overall system performance. The resulting combined model is aware of the uncertainty associated with its predictions, which can help the vehicle autonomy to make decisions with more confidence. The model is validated on real-world urban driving data collected in multiple locations. This validation demonstrates that our approach improves the prediction error of a physics-based model by 25% while successfully identifying the uncertain cases with 82% accuracy.
Humans may be one of the biggest roadblocks keeping fully autonomous vehicles off city streets. If a robot is going to navigate a vehicle safely through downtown Boston, it must be able to predict what nearby drivers, cyclists, and pedestrians are going to do next. Behavior prediction is a tough problem, however, and current artificial intelligence solutions are either too simplistic (they may assume pedestrians always walk in a straight line), too conservative (to avoid pedestrians, the robot just leaves the car in park), or can only forecast the next moves of one agent (roads typically carry many users at once.) MIT researchers have devised a deceptively simple solution to this complicated challenge. They break a multiagent behavior prediction problem into smaller pieces and tackle each one individually, so a computer can solve this complex task in real-time. Their behavior-prediction framework first guesses the relationships between two road users--which car, cyclist, or pedestrian has the right of way, and which agent will yield--and uses those relationships to predict future trajectories for multiple agents.
However, there are a few major problems with the existing methods. First, those methods focus on either the individual patterns or the collective patterns, but very often the movements of objects reflect both individual and collective properties. Second, in some circumstances (e.g., social check-in, and vehicle surveillance), the data points are very sparse; the trajectories of some objects may consist of only one record. One cannot construct meaningful frequent patterns with these trajectories. Finally, the existing methods do not give proper consideration to the time factor.
Predicting the behavior of road agents is a difficult and crucial task for both advanced driver assistance and autonomous driving systems. Traditional confidence measures for this important task often ignore the way predicted trajectories affect downstream decisions and their utilities. In this paper we devise a novel neural network regressor to estimate the utility distribution given the predictions. Based on reasonable assumptions on the utility function, we establish a decision criterion that takes into account the role of prediction in decision making. We train our real-time regressor along with a human driver intent predictor and use it in shared autonomy scenarios where decisions depend on the prediction confidence. We test our system on a realistic urban driving dataset, present the advantage of the resulting system in terms of recall and fall-out performance compared to baseline methods, and demonstrate its effectiveness in intervention and warning use cases.
Multiclass prediction is the problem of classifying an object into a relevant target class. We consider the problem of learning a multiclass predictor that uses only few features, and in particular, the number of used features should increase sub-linearly with the number of possible classes. This implies that features should be shared by several classes. We describe and analyze the ShareBoost algorithm for learning a multiclass predictor that uses few shared features. We prove that ShareBoost efficiently finds a predictor that uses few shared features (if such a predictor exists) and that it has a small generalization error.