As autonomous driving technology matures, end-to-end methodologies have emerged as a leading strategy, promising seamless integration from perception to control via deep learning.
FailureNet observes the poses of vehicles as they approach an intersection and detects whether a failure is present in the autonomy stack, warning cross-traffic of potentially dangerous drivers.
We present a unified probabilistic model that learns a representative set of discrete vehicle actions and predicts the probability of each action given a particular scenario.
Experience replay plays a crucial role in improving the sample efficiency of deep reinforcement learning agents.
Data-driven simulators promise high data-efficiency for driving policy learning.
Simulation has the potential to transform the development of robust algorithms for mobile agents deployed in safety-critical scenarios.
On the other hand, increasing the robustness of these systems is also critical; however, even estimating the model's uncertainty is very challenging due to the cost of sampling-based methods.
We propose a novel controller synthesis involving feedback from pixels, whereby the measurement is a high dimensional signal representing a pixelated image with Red-Green-Blue (RGB) values.
We demonstrate the effectiveness of our algorithm in learning competitive behaviors on a novel multi-agent racing benchmark that requires planning from image observations.
Learning complex robot behaviors through interaction requires structured exploration.
The main contribution of this paper is an efficient time optimal path parametrization algorithm for quadrotors with limited field of view constraints.
Reasoning about uncertain orientations is one of the core problems in many perception tasks such as object pose estimation or motion estimation.
Our main contribution is the concept of learning context maps to improve the prediction task.
Probability theory starts with a distribution function (equivalently a probability measure) as a primitive and builds all other useful concepts, such as law of total probability, Bayes' law, independence, graphical models, point estimate, on it.
While a vehicle is in flight in the FlightGoggles virtual reality environment, exteroceptive sensors are rendered synthetically in real time while all complex extrinsic dynamics are generated organically through the natural interactions of the vehicle.
In this paper, we address the problem of fast depth estimation on embedded systems.
In this work, we present new theoretical results on convolutional generative neural networks, in particular their invertibility (i. e., the recovery of input latent code given the network output).
We define a novel variational network capable of learning from raw camera data of the environment as well as higher level roadmaps to predict (1) a full probability distribution over the possible control commands; and (2) a deterministic control command capable of navigating on the route specified within the map.
The Blackbird unmanned aerial vehicle (UAV) dataset is a large-scale, aggressive indoor flight dataset collected using a custom-built quadrotor platform for use in evaluation of agile perception. Inspired by the potential of future high-speed fully-autonomous drone racing, the Blackbird dataset contains over 10 hours of flight data from 168 flights over 17 flight trajectories and 5 environments at velocities up to $7. 0ms^-1$.
Tensor decompositions such as the canonical format and the tensor train format have been widely utilized to reduce storage costs and operational complexities for high-dimensional data, achieving linear scaling with the input dimension instead of exponential scaling.
Numerical Analysis Numerical Analysis 65F99, 15A23, 15A69
Depth completion, the technique of estimating a dense depth image from sparse depth measurements, has a variety of applications in robotics and autonomous driving.
Ranked #6 on Depth Completion on VOID
Dropout training in deep NNs approximates Bayesian inference in a deep Gaussian process and can thus be used to estimate model uncertainty.
Autonomous driving requires 3D perception of vehicles and other objects in the in environment.
Ranked #17 on 3D Object Detection on KITTI Cars Easy
We consider the problem of dense depth prediction from a sparse set of depth measurements and a single RGB image.
A well-established localization approach combines ray casting with a particle filter, leading to a computationally expensive algorithm that is difficult to run on resource-constrained mobile robots.
Data Structures and Algorithms Robotics
We address the following question: is it possible to reconstruct the geometry of an unknown environment using sparse and incomplete depth measurements?
In this paper, we propose a coordination control algorithm for this problem, assuming stochastic models for the arrival times of the vehicles.
The main contribution of the paper is the introduction of new algorithms, namely, PRM* and RRT*, which are provably asymptotically optimal, i. e., such that the cost of the returned solution converges almost surely to the optimum.
Second, a new algorithm is considered, called the Rapidly-exploring Random Graph (RRG), and it is shown that the cost of the best path in the RRG converges to the optimum almost surely.