In this work, we present a lightweight, tightly-coupled deep depth network and visual-inertial odometry (VIO) system, which can provide accurate state estimates and dense depth maps of the immediate surroundings. Leveraging the proposed lightweight Conditional Variational Autoencoder (CVAE) for depth inference and encoding, we provide the network with previously marginalized sparse features from VIO to increase the accuracy of initial depth prediction and generalization capability. The compact encoded depth maps are then updated jointly with navigation states in a sliding window estimator in order to provide the dense local scene geometry. We additionally propose a novel method to obtain the CVAE's Jacobian which is shown to be more than an order of magnitude faster than previous works, and we additionally leverage First-Estimate Jacobian (FEJ) to avoid recalculation. As opposed to previous works relying on completely dense residuals, we propose to only provide sparse measurements to update the depth code and show through careful experimentation that our choice of sparse measurements and FEJs can still significantly improve the estimated depth maps. Our full system also exhibits state-of-the-art pose estimation accuracy, and we show that it can run in real-time with single-thread execution while utilizing GPU acceleration only for the network and code Jacobian.
相關內容
Tactile sensing is a necessary capability for a robotic hand to perform fine manipulations and interact with the environment. Optical sensors are a promising solution for high-resolution contact estimation. Nevertheless, they are usually not easy to fabricate and require individual calibration in order to acquire sufficient accuracy. In this letter, we propose AllSight, an optical tactile sensor with a round 3D structure potentially designed for robotic in-hand manipulation tasks. AllSight is mostly 3D printed making it low-cost, modular, durable and in the size of a human thumb while with a large contact surface. We show the ability of AllSight to learn and estimate a full contact state, i.e., contact position, forces and torsion. With that, an experimental benchmark between various configurations of illumination and contact elastomers are provided. Furthermore, the robust design of AllSight provides it with a unique zero-shot capability such that a practitioner can fabricate the open-source design and have a ready-to-use state estimation model. A set of experiments demonstrates the accurate state estimation performance of AllSight.
Dense video captioning, a task of localizing meaningful moments and generating relevant captions for videos, often requires a large, expensive corpus of annotated video segments paired with text. In an effort to minimize the annotation cost, we propose ZeroTA, a novel method for dense video captioning in a zero-shot manner. Our method does not require any videos or annotations for training; instead, it localizes and describes events within each input video at test time by optimizing solely on the input. This is accomplished by introducing a soft moment mask that represents a temporal segment in the video and jointly optimizing it with the prefix parameters of a language model. This joint optimization aligns a frozen language generation model (i.e., GPT-2) with a frozen vision-language contrastive model (i.e., CLIP) by maximizing the matching score between the generated text and a moment within the video. We also introduce a pairwise temporal IoU loss to let a set of soft moment masks capture multiple distinct events within the video. Our method effectively discovers diverse significant events within the video, with the resulting captions appropriately describing these events. The empirical results demonstrate that ZeroTA surpasses zero-shot baselines and even outperforms the state-of-the-art few-shot method on the widely-used benchmark ActivityNet Captions. Moreover, our method shows greater robustness compared to supervised methods when evaluated in out-of-domain scenarios. This research provides insight into the potential of aligning widely-used models, such as language generation models and vision-language models, to unlock a new capability: understanding temporal aspects of videos.
One of the key problems in 3D object detection is to reduce the accuracy gap between methods based on LiDAR sensors and those based on monocular cameras. A recently proposed framework for monocular 3D detection based on Pseudo-Stereo has received considerable attention in the community. However, so far these two problems are discovered in existing practices, including (1) monocular depth estimation and Pseudo-Stereo detector must be trained separately, (2) Difficult to be compatible with different stereo detectors and (3) the overall calculation is large, which affects the reasoning speed. In this work, we propose an end-to-end, efficient pseudo-stereo 3D detection framework by introducing a Single-View Diffusion Model (SVDM) that uses a few iterations to gradually deliver right informative pixels to the left image. SVDM allows the entire pseudo-stereo 3D detection pipeline to be trained end-to-end and can benefit from the training of stereo detectors. Afterwards, we further explore the application of SVDM in depth-free stereo 3D detection, and the final framework is compatible with most stereo detectors. Among multiple benchmarks on the KITTI dataset, we achieve new state-of-the-art performance.
Deploying autonomous robots in crowded indoor environments usually requires them to have accurate dynamic obstacle perception. Although plenty of previous works in the autonomous driving field have investigated the 3D object detection problem, the usage of dense point clouds from a heavy LiDAR and their high computation cost for learning-based data processing make those methods not applicable to small robots, such as vision-based UAVs with small onboard computers. To address this issue, we propose a lightweight 3D dynamic obstacle detection and tracking (DODT) method based on an RGB-D camera, which is designed for low-power robots with limited computing power. Our method adopts a novel ensemble detection strategy, combining multiple computationally efficient but low-accuracy detectors to achieve real-time high-accuracy obstacle detection. Besides, we introduce a new feature-based data association method to prevent mismatches and use the Kalman filter with the constant acceleration model to track detected obstacles. In addition, our system includes an optional and auxiliary learning-based module to enhance the obstacle detection range and dynamic obstacle identification. The users can determine whether or not to run this module based on the available computation resources. The proposed method is implemented in a small quadcopter, and the experiments prove that the algorithm can make the robot detect dynamic obstacles and navigate dynamic environments safely.
Localization for autonomous robots in prior maps is crucial for their functionality. This paper offers a solution to this problem for indoor environments called InstaLoc, which operates on an individual lidar scan to localize it within a prior map. We draw on inspiration from how humans navigate and position themselves by recognizing the layout of distinctive objects and structures. Mimicking the human approach, InstaLoc identifies and matches object instances in the scene with those from a prior map. As far as we know, this is the first method to use panoptic segmentation directly inferring on 3D lidar scans for indoor localization. InstaLoc operates through two networks based on spatially sparse tensors to directly infer dense 3D lidar point clouds. The first network is a panoptic segmentation network that produces object instances and their semantic classes. The second smaller network produces a descriptor for each object instance. A consensus based matching algorithm then matches the instances to the prior map and estimates a six degrees of freedom (DoF) pose for the input cloud in the prior map. The significance of InstaLoc is that it has two efficient networks. It requires only one to two hours of training on a mobile GPU and runs in real-time at 1 Hz. Our method achieves between two and four times more detections when localizing, as compared to baseline methods, and achieves higher precision on these detections.
Geometric navigation is nowadays a well-established field of robotics and the research focus is shifting towards higher-level scene understanding, such as Semantic Mapping. When a robot needs to interact with its environment, it must be able to comprehend the contextual information of its surroundings. This work focuses on classifying and localising objects within a map, which is under construction (SLAM) or already built. To further explore this direction, we propose a framework that can autonomously detect and localize predefined objects in a known environment using a multi-modal sensor fusion approach (combining RGB and depth data from an RGB-D camera and a lidar). The framework consists of three key elements: understanding the environment through RGB data, estimating depth through multi-modal sensor fusion, and managing artifacts (i.e., filtering and stabilizing measurements). The experiments show that the proposed framework can accurately detect 98% of the objects in the real sample environment, without post-processing, while 85% and 80% of the objects were mapped using the single RGBD camera or RGB + lidar setup respectively. The comparison with single-sensor (camera or lidar) experiments is performed to show that sensor fusion allows the robot to accurately detect near and far obstacles, which would have been noisy or imprecise in a purely visual or laser-based approach.
A key challenge in robotic manipulation in open domains is how to acquire diverse and generalizable skills for robots. Recent research in one-shot imitation learning has shown promise in transferring trained policies to new tasks based on demonstrations. This feature is attractive for enabling robots to acquire new skills and improving task and motion planning. However, due to limitations in the training dataset, the current focus of the community has mainly been on simple cases, such as push or pick-place tasks, relying solely on visual guidance. In reality, there are many complex skills, some of which may even require both visual and tactile perception to solve. This paper aims to unlock the potential for an agent to generalize to hundreds of real-world skills with multi-modal perception. To achieve this, we have collected a dataset comprising over 110,000 \emph{contact-rich} robot manipulation sequences across diverse skills, contexts, robots, and camera viewpoints, all collected \emph{in the real world}. Each sequence in the dataset includes visual, force, audio, and action information, along with a corresponding human demonstration video. We have invested significant efforts in calibrating all the sensors and ensuring a high-quality dataset. The dataset is made publicly available at rh20t.github.io
Multimodal learning helps to comprehensively understand the world, by integrating different senses. Accordingly, multiple input modalities are expected to boost model performance, but we actually find that they are not fully exploited even when the multimodal model outperforms its uni-modal counterpart. Specifically, in this paper we point out that existing multimodal discriminative models, in which uniform objective is designed for all modalities, could remain under-optimized uni-modal representations, caused by another dominated modality in some scenarios, e.g., sound in blowing wind event, vision in drawing picture event, etc. To alleviate this optimization imbalance, we propose on-the-fly gradient modulation to adaptively control the optimization of each modality, via monitoring the discrepancy of their contribution towards the learning objective. Further, an extra Gaussian noise that changes dynamically is introduced to avoid possible generalization drop caused by gradient modulation. As a result, we achieve considerable improvement over common fusion methods on different multimodal tasks, and this simple strategy can also boost existing multimodal methods, which illustrates its efficacy and versatility. The source code is available at \url{//github.com/GeWu-Lab/OGM-GE_CVPR2022}.
We present a monocular Simultaneous Localization and Mapping (SLAM) using high level object and plane landmarks, in addition to points. The resulting map is denser, more compact and meaningful compared to point only SLAM. We first propose a high order graphical model to jointly infer the 3D object and layout planes from single image considering occlusions and semantic constraints. The extracted cuboid object and layout planes are further optimized in a unified SLAM framework. Objects and planes can provide more semantic constraints such as Manhattan and object supporting relationships compared to points. Experiments on various public and collected datasets including ICL NUIM and TUM mono show that our algorithm can improve camera localization accuracy compared to state-of-the-art SLAM and also generate dense maps in many structured environments.
Dense video captioning aims to generate text descriptions for all events in an untrimmed video. This involves both detecting and describing events. Therefore, all previous methods on dense video captioning tackle this problem by building two models, i.e. an event proposal and a captioning model, for these two sub-problems. The models are either trained separately or in alternation. This prevents direct influence of the language description to the event proposal, which is important for generating accurate descriptions. To address this problem, we propose an end-to-end transformer model for dense video captioning. The encoder encodes the video into appropriate representations. The proposal decoder decodes from the encoding with different anchors to form video event proposals. The captioning decoder employs a masking network to restrict its attention to the proposal event over the encoding feature. This masking network converts the event proposal to a differentiable mask, which ensures the consistency between the proposal and captioning during training. In addition, our model employs a self-attention mechanism, which enables the use of efficient non-recurrent structure during encoding and leads to performance improvements. We demonstrate the effectiveness of this end-to-end model on ActivityNet Captions and YouCookII datasets, where we achieved 10.12 and 6.58 METEOR score, respectively.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191