We propose a general self-supervised learning approach for spatial perception tasks, such as estimating the pose of an object relative to the robot, from onboard sensor readings. The model is learned from training episodes, by relying on: a continuous state estimate, possibly inaccurate and affected by odometry drift; and a detector, that sporadically provides supervision about the target pose. We demonstrate the general approach in three different concrete scenarios: a simulated robot arm that visually estimates the pose of an object of interest; a small differential drive robot using 7 infrared sensors to localize a nearby wall; an omnidirectional mobile robot that localizes itself in an environment from camera images. Quantitative results show that the approach works well in all three scenarios, and that explicitly accounting for uncertainty yields statistically significant performance improvements.
VEDECOM Institute（VEDECOM研究所）；French-German Research Institute of Saint-Louis（圣路易法德研究所）；Université Paris-Saclay（巴黎萨克雷大学）；CNRS（法国国家科学研究中心）；CentraleSupelec（中央理工-高等电力学院）
Nowadays, supervised deep learning techniques yield the best state-of-the-art prediction performances for a wide variety of computer vision tasks. However, such supervised techniques generally require a large amount of manually labeled training data. In the context of autonomous vehicles perception, this requirement is critical, as the distribution of sensor data can continuously change and include several unexpected variations. It turns out that a category of learning techniques, referred to as self-supervised learning (SSL), consists of replacing the manual labeling effort by an automatic la…
Montreal Robotics and Embodied AI Lab（蒙特利尔机器人与具身人工智能实验室）；Mila（米拉人工智能研究所）；Université de Montréal（蒙特利尔大学）；Denso（电装公司）
While modern deep neural networks are performant perception modules, performance (accuracy) alone is insufficient, particularly for safety-critical robotic applications such as self-driving vehicles. Robot autonomy stacks also require these otherwise blackbox models to produce reliable and calibrated measures of confidence on their predictions. Existing approaches estimate uncertainty from these neural network perception stacks by modifying network architectures, inference procedure, or loss functions. However, in general, these methods lack calibration, meaning that the predictive uncertainti…
Does Knowledge About Perceptual Uncertainty Help an Agent in Automated Driving?
Institute of Mathematics Technical University of Berlin Berlin, Germany；Department of Mathematics University of Wuppertal Wuppertal, Germany；Faculty of Computer Science Ruhr University Bochum Bochum, Germany
Technical University of Munich（慕尼黑工业大学）；Institute for Automotive Engineering, Munich Institute of Robotics and Machine Intelligence, School of Engineering and Design（汽车工程研究所，慕尼黑机器人与机器智能研究所，工程与设计学院）
Northwestern University（西北大学）；University of California, Irvine（加利福尼亚大学欧文分校）
In the development of advanced driver-assistance systems (ADAS) and autonomous vehicles, machine learning techniques that are based on deep neural networks (DNNs) have been widely used for vehicle perception. These techniques offer significant improvement on average perception accuracy over traditional methods, however, have been shown to be susceptible to adversarial attacks, where small perturbations in the input may cause significant errors in the perception results and lead to system failure. Most prior works addressing such adversarial attacks focus only on the sensing and perception modu…
Hyper-V2X: Hypernetworks for Estimating Epistemic and Aleatoric Uncertainty in Cooperative Bird's-Eye-View Semantic Segmentation
CARISSMA Institute for Electric, COnnected, and Secure Mobility (C-ECOS), Technische Hochschule Ingolstadt（CARISSMA电动、连接与安全移动研究所（C-ECOS）、因戈尔施塔特技术大学）；University of Applied Sciences Aschaffenburg（阿施发堡应用科学大学）
Learning-based perception and prediction modules in modern autonomous driving systems typically rely on expensive human annotation and are designed to perceive only a handful of predefined object categories. This closed-set paradigm is insufficient for the safety-critical autonomous driving task, where the autonomous vehicle needs to process arbitrarily many types of traffic participants and their motion behaviors in a highly dynamic world. To address this difficulty, this paper pioneers a novel and challenging direction, i.e., training perception and prediction models to understand open-set m…
Gaussian Mixture-Based Inverse Perception Contract for Uncertainty-Aware Robot Navigation
Department of Computer Science, Columbia University（计算机科学系，哥伦比亚大学）；Department of Computer Science and Engineering, Texas A&M University（计算机科学与工程系，德克萨斯大学）
Uncertainty-Informed Active Perception for Open Vocabulary Object Goal Navigation
Center for Robotics, University of Bonn（波恩大学机器人中心）；MAVLab, TU Delft（代尔夫特理工大学MAVLab）；Lamarr Institute for Machine Learning and Artificial Intelligence（机器学习与人工智能拉马尔研究所）
Learning visuomotor control policies in robotic systems is a fundamental problem when aiming for long-term behavioral autonomy. Recent supervised-learning-based vision and motion perception systems, however, are often separately built with limited capabilities, while being restricted to few behavioral skills such as passive visual odometry (VO) or mobile robot visual localization. Here we propose an approach to unify those successful robot perception systems for active target-driven navigation tasks via reinforcement learning (RL). Our method temporally incorporates compact motion and visual p…
Credibility-Aware Learning and Control for Safe USV Navigation under Perception Uncertainty
School of Information Engineering, Henan University of Science and Technology（河南科技大学信息工程学院）；Shenzhen Research Institute of Big Data（深圳大数据研究院）；School of Logistics Engineering, Shanghai Maritime University（上海 Maritime University物流工程学院）；Shenzhen Technology University（深圳科技大学）；School of Computer Science, Wuhan University（武汉大学计算机学院）；School of Software Engineering, Tongji University（同济大学软件工程学院）
We present self-supervised geometric perception (SGP), the first general framework to learn a feature descriptor for correspondence matching without any ground-truth geometric model labels (e.g., camera poses, rigid transformations). Our first contribution is to formulate geometric perception as an optimization problem that jointly optimizes the feature descriptor and the geometric models given a large corpus of visual measurements (e.g., images, point clouds). Under this optimization formulation, we show that two important streams of research in vision, namely robust model fitting and deep fe…
GE Research（通用电气研究院）；Motional（Motional公司）；GE Digital（通用电气数字部门）
Off-road autonomous unmanned ground vehicles (UGVs) are being developed for military and commercial use to deliver crucial supplies in remote locations, help with mapping and surveillance, and to assist war-fighters in contested environments. Due to complexity of the off-road environments and variability in terrain, lighting conditions, diurnal and seasonal changes, the models used to perceive the environment must handle a lot of input variability. Current datasets used to train perception models for off-road autonomous navigation lack of diversity in seasons, locations, semantic classes, as w…
TRIAGE: Type-Routed Interventions via Aleatoric-Epistemic Gated Estimation in Robotic Manipulation and Adaptive Perception -- Don't Treat All Uncertainty the Same
University of Illinois at Chicago（伊利诺伊大学香槟分校）；Intel Labs（英特尔实验室）
Facebook AI Research（Facebook AI研究院）；Carnegie Mellon University（卡内基梅隆大学）；UIUC（伊利诺伊大学厄巴纳-香槟分校）；UC Berkeley（加州大学伯克利分校）
In this paper, we explore how we can build upon the data and models of Internet images and use them to adapt to robot vision without requiring any extra labels. We present a framework called Self-supervised Embodied Active Learning (SEAL). It utilizes perception models trained on internet images to learn an active exploration policy. The observations gathered by this exploration policy are labelled using 3D consistency and used to improve the perception model. We build and utilize 3D semantic maps to learn both action and perception in a completely self-supervised manner. The semantic map is u…
Istanbul Technical University（伊斯坦布尔理工大学）；Turkish-German University（土耳其-德国大学）
We investigate how to utilize predictive models for selecting appropriate motion planning strategies based on perception uncertainty estimation for agile unmanned aerial vehicle (UAV) navigation tasks. Although there are variety of motion planning and perception algorithms for such tasks, the impact of perception uncertainty is not explicitly handled in many of the current motion algorithms, which leads to performance loss in real-life scenarios where the measurement are often noisy due to external disturbances. We develop a novel framework for embedding perception uncertainty to high level mo…
This work focuses on improving uncertainty estimation in the field of object classification from RGB images and demonstrates its benefits in two robotic applications. We employ a (BNN), and evaluate two practical inference techniques to obtain better uncertainty estimates, namely Concrete Dropout (CDP) and Kronecker-factored Laplace Approximation (LAP). We show a performance increase using more reliable uncertainty estimates as unary potentials within a Conditional Random Field (CRF), which is able to incorporate contextual information as well. Furthermore, the obtained uncertainties are explo…
Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）；Honda Research Institute（本田研究院）
3D object trackers usually require training on large amounts of annotated data that is expensive and time-consuming to collect. Instead, we propose leveraging vast unlabeled datasets by self-supervised metric learning of 3D object trackers, with a focus on data association. Large scale annotations for unlabeled data are cheaply obtained by automatic object detection and association across frames. We show how these self-supervised annotations can be used in a principled manner to learn point-cloud embeddings that are effective for 3D tracking. We estimate and incorporate uncertainty in self-sup…
Uncertainty Quantification of Set-Membership Estimation in Control and Perception: Revisiting the Minimum Enclosing Ellipsoid
Princeton University（普林斯顿大学）；LAAS-CNRS（法国国家科学研究中心LAAS实验室）；Toulouse School of Economics (TSE)（图卢兹经济学院）；School of Engineering and Applied Sciences, Harvard University（哈佛大学工程与应用科学学院）
University of Bonn（波恩大学）；University of Oxford（牛津大学）；Lamarr Institute for Machine Learning and Artificial Intelligence（拉马尔机器学习与人工智能研究所）；La Sapienza University of Rome（罗马第一大学）
Agricultural robots have the prospect to enable more efficient and sustainable agricultural production of food, feed, and fiber. Perception of crops and weeds is a central component of agricultural robots that aim to monitor fields and assess the plants as well as their growth stage in an automatic manner. Semantic perception mostly relies on deep learning using supervised approaches, which require time and qualified workers to label fairly large amounts of data. In this paper, we look into the problem of reducing the amount of labels without compromising the final segmentation performance. Fo…
University of California, Berkeley（加州大学伯克利分校）；Toyota Research Institute（丰田研究院）
Cables are commonplace in homes, hospitals, and industrial warehouses and are prone to tangling. This paper extends prior work on autonomously untangling long cables by introducing novel uncertainty quantification metrics and actions that interact with the cable to reduce perception uncertainty. We present Sliding and Grasping for Tangle Manipulation 2.0 (SGTM 2.0), a system that autonomously untangles cables approximately 3 meters in length with a bilateral robot using estimates of uncertainty at each step to inform actions. By interactively reducing uncertainty, Sliding and Grasping for Tang…
Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）
In this work, we consider the problem of learning a perception model for monocular robot navigation using few annotated images. Using a Vision Transformer (ViT) pretrained with a label-free self-supervised method, we successfully train a coarse image segmentation model for the Duckietown environment using 70 training images. Our model performs coarse image segmentation at the 8x8 patch level, and the inference resolution can be adjusted to balance prediction granularity and real-time perception constraints. We study how best to adapt a ViT to our task and environment, and find that some lightw…
Visual place recognition techniques based on deep learning, which have imposed themselves as the state-of-the-art in recent years, do not generalize well to environments visually different from the training set. Thus, to achieve top performance, it is sometimes necessary to fine-tune the networks to the target environment. To this end, we propose a self-supervised domain calibration procedure based on robust pose graph optimization from Simultaneous Localization and Mapping (SLAM) as the supervision signal without requiring GPS or manual labeling. Moreover, we leverage the procedure to improve…
Most real-world 3D sensors such as LiDARs perform fixed scans of the entire environment, while being decoupled from the recognition system that processes the sensor data. In this work, we propose a method for 3D object recognition using light curtains, a resource-efficient controllable sensor that measures depth at user-specified locations in the environment. Crucially, we propose using prediction uncertainty of a deep learning based 3D point cloud detector to guide active perception. Given a neural network's uncertainty, we derive an optimization objective to place light curtains using the pr…
