Add to Chrome
Add to Firefox
Add to EdgeYang Cheng
On Large Language Models' Hallucination with Regard to Known Facts
Mar 29, 2024
Large language models are successful in answering factoid questions but are also prone to hallucination.We investigate the phenomenon of LLMs possessing correct answer knowledge yet still hallucinating from the perspective of inference dynamics, an area not previously covered in studies on hallucinations.We are able to conduct this analysis via two key ideas.First, we identify the factual questions that query the same triplet knowledge but result in different answers. The difference between the model behaviors on the correct and incorrect outputs hence suggests the patterns when hallucinations happen. Second, to measure the pattern, we utilize mappings from the residual streams to vocabulary space. We reveal the different dynamics of the output token probabilities along the depths of layers between the correct and hallucinated cases. In hallucinated cases, the output token's information rarely demonstrates abrupt increases and consistent superiority in the later stages of the model. Leveraging the dynamic curve as a feature, we build a classifier capable of accurately detecting hallucinatory predictions with an 88\% success rate. Our study shed light on understanding the reasons for LLMs' hallucinations on their known facts, and more importantly, on accurately predicting when they are hallucinating.
Truck Parking Usage Prediction with Decomposed Graph Neural Networks
Jan 23, 2024Truck parking on freight corridors faces various challenges, such as insufficient parking spaces and compliance with Hour-of-Service (HOS) regulations. These constraints often result in unauthorized parking practices, causing safety concerns. To enhance the safety of freight operations, providing accurate parking usage prediction proves to be a cost-effective solution. Despite the existing research demonstrating satisfactory accuracy for predicting individual truck parking site usage, few approaches have been proposed for predicting usage with spatial dependencies of multiple truck parking sites. We present the Regional Temporal Graph Neural Network (RegT-GCN) as a predictive framework for assessing parking usage across the entire state to provide better truck parking information and mitigate unauthorized parking. The framework leverages the topological structures of truck parking site distributions and historical parking data to predict occupancy rates across a state. To achieve this, we introduce a Regional Decomposition approach, which effectively captures the geographical characteristics. We also introduce the spatial module working efficiently with the temporal module. Evaluation results demonstrate that the proposed model surpasses other baseline models, improving the performance by more than $20\%$ compared with the original model. The proposed model allows truck parking sites' percipience of the topological structures and provides higher performance.
Keypoint-based Stereophotoclinometry for Characterizing and Navigating Small Bodies: A Factor Graph Approach
Dec 11, 2023
This paper proposes the incorporation of techniques from stereophotoclinometry (SPC) into a keypoint-based structure-from-motion (SfM) system to estimate the surface normal and albedo at detected landmarks to improve autonomous surface and shape characterization of small celestial bodies from in-situ imagery. In contrast to the current state-of-the-practice method for small body shape reconstruction, i.e., SPC, which relies on human-in-the-loop verification and high-fidelity a priori information to achieve accurate results, we forego the expensive maplet estimation step and instead leverage dense keypoint measurements and correspondences from an autonomous keypoint detection and matching method based on deep learning to provide the necessary photogrammetric constraints. Moreover, we develop a factor graph-based approach allowing for simultaneous optimization of the spacecraft's pose, landmark positions, Sun-relative direction, and surface normals and albedos via fusion of Sun sensor measurements and image keypoint measurements. The proposed framework is validated on real imagery of the Cornelia crater on Asteroid 4 Vesta, along with pose estimation and mapping comparison against an SPC reconstruction, where we demonstrate precise alignment to the SPC solution without relying on any a priori camera pose and topography information or humans-in-the-loop
PL-UNeXt: Per-stage Edge Detail and Line Feature Guided Segmentation for Power Line Detection
Mar 08, 2023
Power line detection is a critical inspection task for electricity companies and is also useful in avoiding drone obstacles. Accurately separating power lines from the surrounding area in the aerial image is still challenging due to the intricate background and low pixel ratio. In order to properly capture the guidance of the spatial edge detail prior and line features, we offer PL-UNeXt, a power line segmentation model with a booster training strategy. We design edge detail heads computing the loss in edge space to guide the lower-level detail learning and line feature heads generating auxiliary segmentation masks to supervise higher-level line feature learning. Benefited from this design, our model can reach 70.6 F1 score (+1.9%) on TTPLA and 68.41 mIoU (+5.2%) on VITL (without utilizing IR images), while preserving a real-time performance due to few inference parameters.
LunarNav: Crater-based Localization for Long-range Autonomous Lunar Rover Navigation
Jan 03, 2023
The Artemis program requires robotic and crewed lunar rovers for resource prospecting and exploitation, construction and maintenance of facilities, and human exploration. These rovers must support navigation for 10s of kilometers (km) from base camps. A lunar science rover mission concept - Endurance-A, has been recommended by the new Decadal Survey as the highest priority medium-class mission of the Lunar Discovery and Exploration Program, and would be required to traverse approximately 2000 km in the South Pole-Aitkin (SPA) Basin, with individual drives of several kilometers between stops for downlink. These rover mission scenarios require functionality that provides onboard, autonomous, global position knowledge ( aka absolute localization). However, planetary rovers have no onboard global localization capability to date; they have only used relative localization, by integrating combinations of wheel odometry, visual odometry, and inertial measurements during each drive to track position relative to the start of each drive. In this work, we summarize recent developments from the LunarNav project, where we have developed algorithms and software to enable lunar rovers to estimate their global position and heading on the Moon with a goal performance of position error less than 5 meters (m) and heading error less than 3-degree, 3-sigma, in sunlit areas. This will be achieved autonomously onboard by detecting craters in the vicinity of the rover and matching them to a database of known craters mapped from orbit. The overall technical framework consists of three main elements: 1) crater detection, 2) crater matching, and 3) state estimation. In previous work, we developed crater detection algorithms for three different sensing modalities. Our results suggest that rover localization with an error less than 5 m is highly probable during daytime operations.
Rega-Net:Retina Gabor Attention for Deep Convolutional Neural Networks
Nov 23, 2022
Extensive research works demonstrate that the attention mechanism in convolutional neural networks (CNNs) effectively improves accuracy. But little works design attention mechanisms using large receptive fields. In this work, we propose a novel attention method named Rega-net to increase CNN accuracy by enlarging the receptive field. Inspired by the mechanism of the human retina, we design convolutional kernels to resemble the non-uniformly distributed structure of the human retina. Then, we sample variable-resolution values in the Gabor function distribution and fill these values in retina-like kernels. This distribution allows important features to be more visible in the center position of the receptive field. We further design an attention module including these retina-like kernels. Experiments demonstrate that our Rega-Net achieves 79.963\% top-1 accuracy on ImageNet-1K classification and 43.1\% mAP on COCO2017 object detection. The mAP of the Rega-Net increased by up to 3.5\% compared to baseline networks.
Lunar Rover Localization Using Craters as Landmarks
Mar 18, 2022
Onboard localization capabilities for planetary rovers to date have used relative navigation, by integrating combinations of wheel odometry, visual odometry, and inertial measurements during each drive to track position relative to the start of each drive. At the end of each drive, a ground-in-the-loop (GITL) interaction is used to get a position update from human operators in a more global reference frame, by matching images or local maps from onboard the rover to orbital reconnaissance images or maps of a large region around the rover's current position. Autonomous rover drives are limited in distance so that accumulated relative navigation error does not risk the possibility of the rover driving into hazards known from orbital images. However, several rover mission concepts have recently been studied that require much longer drives between GITL cycles, particularly for the Moon. These concepts require greater autonomy to minimize GITL cycles to enable such large range; onboard global localization is a key element of such autonomy. Multiple techniques have been studied in the past for onboard rover global localization, but a satisfactory solution has not yet emerged. For the Moon, the ubiquitous craters offer a new possibility, which involves mapping craters from orbit, then recognizing crater landmarks with cameras and-or a lidar onboard the rover. This approach is applicable everywhere on the Moon, does not require high resolution stereo imaging from orbit as some other approaches do, and has potential to enable position knowledge with order of 5 to 10 m accuracy at all times. This paper describes our technical approach to crater-based lunar rover localization and presents initial results on crater detection using 3D point cloud data from onboard lidar or stereo cameras, as well as using shading cues in monocular onboard imagery.
Window Filtering Algorithm for Pulsed Light Coherent Combining of Low Repetition Frequency
Mar 03, 2022
The multi-dithering method has been well verified in phase locking of polarization coherent combination experiment. However, it is hard to apply to low repetition frequency pulsed lasers, since there exists an overlap frequency domain between pulse laser and the amplitude phase noise and traditional filters cannot effectively separate phase noise. Aiming to solve the problem in this paper, we propose a novel method of pulse noise detection, identification, and filtering based on the autocorrelation characteristics between noise signals. In the proposed algorithm, a self-designed window algorithm is used to identify the pulse, and then the pulse signal group in the window is replaced by interpolation, which effectively filter the pulse signal doped in the phase noise within 0.1 ms. After filtering the pulses in the phase noise, the phase difference of two pulsed beams (10 kHz) is successfully compensated to zero in 1 ms, and the coherent combination of closed-loop phase lock is realized. At the same time, the phase correction times are few, the phase lock effect is stable, and the final light intensity increases to the ideal value (0.9 Imax).
Total Least Squares for Optimal Pose Estimation
Jun 22, 2021
This work provides a theoretical framework for the pose estimation problem using total least squares for vector observations from landmark features. First, the optimization framework is formulated for the pose estimation problem with observation vectors extracted from point cloud features. Then, error-covariance expressions are derived. The attitude and position solutions obtained via the derived optimization framework are proven to reach the bounds defined by the Cram\'er-Rao lower bound under the small angle approximation of attitude errors. The measurement data for the simulation of this problem is provided through a series of vector observation scans, and a fully populated observation noise-covariance matrix is assumed as the weight in the cost function to cover for the most general case of the sensor uncertainty. Here, previous derivations are expanded for the pose estimation problem to include more generic cases of correlations in the errors than previously cases involving an isotropic noise assumption. The proposed solution is simulated in a Monte-Carlo framework with 10,000 samples to validate the error-covariance analysis.
Rover Relocalization for Mars Sample Return by Virtual Template Synthesis and Matching
Mar 05, 2021
We consider the problem of rover relocalization in the context of the notional Mars Sample Return campaign. In this campaign, a rover (R1) needs to be capable of autonomously navigating and localizing itself within an area of approximately 50 x 50 m using reference images collected years earlier by another rover (R0). We propose a visual localizer that exhibits robustness to the relatively barren terrain that we expect to find in relevant areas, and to large lighting and viewpoint differences between R0 and R1. The localizer synthesizes partial renderings of a mesh built from reference R0 images and matches those to R1 images. We evaluate our method on a dataset totaling 2160 images covering the range of expected environmental conditions (terrain, lighting, approach angle). Experimental results show the effectiveness of our approach. This work informs the Mars Sample Return campaign on the choice of a site where Perseverance (R0) will place a set of sample tubes for future retrieval by another rover (R1).