ML is being deployed in complex, real-world scenarios where errors have impactful consequences. In these systems, thorough testing of the ML pipelines is critical. A key component in ML deployment pipelines is the curation of labeled training data. Common practice in the ML literature assumes that labels are the ground truth. However, in our experience in a large autonomous vehicle development center, we have found that vendors can often provide erroneous labels, which can lead to downstream safety risks in trained models.

Self-supervised learning has emerged as a powerful tool for depth and ego-motion estimation, leading to state-of-the-art results on benchmark datasets. However, one significant limitation shared by current methods is the assumption of a known parametric camera model - usually the standard pinhole geometry - leading to failure when applied to imaging systems that deviate significantly from this assumption (e.g., catadioptric cameras or underwater imaging). In this work, we show that self-supervision can be used to learn accurate depth and ego-motion estimation without prior knowledge of the camera model. Inspired by the geometric model of Grossberg and Nayar, we introduce Neural Ray Surfaces (NRS), convolutional networks that represent pixel-wise projection rays, approximating a wide range of cameras. NRS are fully differentiable and can be learned end-to-end from unlabeled raw videos. We demonstrate the use of NRS for self-supervised learning of visual odometry and depth estimation from raw videos obtained using a wide variety of camera systems, including pinhole, fisheye, and catadioptric.

Although cameras are ubiquitous, robotic platforms typically rely on active sensors like LiDAR for direct 3D perception. In this work, we propose a novel self-supervised monocular depth estimation method combining geometry with a new deep network, PackNet, learned only from unlabeled monocular videos. Our architecture leverages novel symmetrical packing and unpacking blocks to jointly learn to compress and decompress detail-preserving representations using 3D convolutions. Although self-supervised, our method outperforms other self, semi, and fully supervised methods on the KITTI benchmark. The 3D inductive bias in PackNet enables it to scale with input resolution and number of parameters without overfitting, generalizing better on out-of-domain data such as the NuScenes dataset. Furthermore, it does not require large-scale supervised pretraining on ImageNet and can run in real-time. Finally, we release DDAD (Dense Depth for Automated Driving), a new urban driving dataset with more challenging and accurate depth evaluation, thanks to longer-range and denser ground-truth depth generated from high-density LiDARs mounted on a fleet of self-driving cars operating world-wide.

In autonomous driving, accurately estimating the state of surrounding obstacles is critical for safe and robust path planning. However, this perception task is difficult, particularly for generic obstacles/objects, due to appearance and occlusion changes. To tackle this problem, we propose an end-to-end deep learning framework for LIDAR-based flow estimation in bird's eye view (BeV). Our method takes consecutive point cloud pairs as input and produces a 2-D BeV flow grid describing the dynamic state of each cell. The experimental results show that the proposed method not only estimates 2-D BeV flow accurately but also improves tracking performance of both dynamic and static objects.

Recent techniques in self-supervised monocular depth estimation are approaching the performance of supervised methods, but operate in low resolution only. We show that high resolution is key towards high-fidelity self-supervised monocular depth prediction. Inspired by recent deep learning methods for Single-Image Super-Resolution, we propose a subpixel convolutional layer extension for depth super-resolution that accurately synthesizes high-resolution disparities from their corresponding low-resolution convolutional features. In addition, we introduce a differentiable flip-augmentation layer that accurately fuses predictions from the image and its horizontally flipped version, reducing the effect of left and right shadow regions generated in the disparity map due to occlusions. Both contributions provide significant performance gains over the state-of-the-art in self-supervised depth and pose estimation on the public KITTI benchmark. A video of our approach can be found at https://youtu.be/jKNgBeBMx0I.

Robotic systems typically require memory recall mechanisms for a variety of tasks including localization, mapping, planning, visualization etc. We argue for a novel memory recall framework that enables more complex inference schemas by separating the computation from its associated data. In this work we propose a shared, centralized data persistence layer that maintains an ensemble of online, situationally-aware robot states. This is realized through a queryable graph-database with an accompanying key-value store for larger data. In turn, this approach is scalable and enables a multitude of capabilities such as experience-based learning and long-term autonomy. Using multi-modal simultaneous localization and mapping and a few example use-cases, we demonstrate the versatility and extensible nature that centralized persistence and SLAMinDB can provide. In order to support the notion of life-long autonomy, we envision robots to be endowed with such a persistence model, enabling them to revisit previous experiences and improve upon their existing task-specific capabilities.

Many model-based Visual Odometry (VO) algorithms have been proposed in the past decade, often restricted to the type of camera optics, or the underlying motion manifold observed. We envision robots to be able to learn and perform these tasks, in a minimally supervised setting, as they gain more experience. To this end, we propose a fully trainable solution to visual ego-motion estimation for varied camera optics. We propose a visual ego-motion learning architecture that maps observed optical flow vectors to an ego-motion density estimate via a Mixture Density Network (MDN). By modeling the architecture as a Conditional Variational Autoencoder (C-VAE), our model is able to provide introspective reasoning and prediction for ego-motion induced scene-flow. Additionally, our proposed model is especially amenable to bootstrapped ego-motion learning in robots where the supervision in ego-motion estimation for a particular camera sensor can be obtained from standard navigation-based sensor fusion strategies (GPS/INS and wheel-odometry fusion). Through experiments, we show the utility of our proposed approach in enabling the concept of self-supervised learning for visual ego-motion estimation in autonomous robots.

State of the art sensors within a single autonomous vehicle (AV) can produce video and LIDAR data at rates greater than 30 GB/hour. Unsurprisingly, even small AV research teams can accumulate tens of terabytes of sensor data from multiple trips and multiple vehicles. AV practitioners would like to extract information about specific locations or specific situations for further study, but are often unable to. Queries over AV sensor data are different from generic analytics or spatial queries because they demand reasoning about fields of view as well as heavy computation to extract features from scenes. In this article and demo we present Vroom, a system for ad-hoc queries over AV sensor databases. Vroom combines domain specific properties of AV datasets with selective indexing and multi-query optimization to address challenges posed by AV sensor data.

Traditional stereo algorithms have focused their efforts on reconstruction quality and have largely avoided prioritizing for run time performance. Robots, on the other hand, require quick maneuverability and effective computation to observe its immediate environment and perform tasks within it. In this work, we propose a high-performance and tunable stereo disparity estimation method, with a peak frame-rate of 120Hz (VGA resolution, on a single CPU-thread), that can potentially enable robots to quickly reconstruct their immediate surroundings and maneuver at high-speeds. Our key contribution is a disparity estimation algorithm that iteratively approximates the scene depth via a piece-wise planar mesh from stereo imagery, with a fast depth validation step for semi-dense reconstruction. The mesh is initially seeded with sparsely matched keypoints, and is recursively tessellated and refined as needed (via a resampling stage), to provide the desired stereo disparity accuracy. The inherent simplicity and speed of our approach, with the ability to tune it to a desired reconstruction quality and runtime performance makes it a compelling solution for applications in high-speed vehicles.

We propose a simple and useful idea based on cross-ratio constraint for wide-baseline matching and 3D reconstruction. Most existing methods exploit feature points and planes from images. Lines have always been considered notorious for both matching and reconstruction due to the lack of good line descriptors. We propose a method to generate and match new points using virtual lines constructed using pairs of keypoints, which are obtained using standard feature point detectors. We use cross-ratio constraints to obtain an initial set of new point matches, which are subsequently used to obtain line correspondences. We develop a method that works for both calibrated and uncalibrated camera configurations. We show compelling line-matching and large-scale 3D reconstruction.

The paper describes the system developed by researchers from MIT for the Defense Advanced Research Projects Agency's (DARPA) Virtual Robotics Challenge (VRC), held in June 2013. The VRC was the first competition in the DARPA Robotics Challenge (DRC), a program that aims to “develop ground robotic capabilities to execute complex tasks in dangerous, degraded, human-engineered environments”. The VRC required teams to guide a model of Boston Dynamics' humanoid robot, Atlas, through driving, walking, and manipulation tasks in simulation. Team MIT's user interface, the Viewer, provided the operator with a unified representation of all available information. A 3D rendering of the robot depicted its most recently estimated body state with respect to the surrounding environment, represented by point clouds and texture-mapped meshes as sensed by on-board LIDAR and fused over time.