Peng Yin

Peng Yin
Carnegie Mellon University | CMU · Robotics Institute

Doctor of Engineering
Project Scientist at CMU, RI, AirLab, aiming at providing visual general localization (VGI) system for robotics.

About

37
Publications
4,064
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
290
Citations
Introduction
I am a PostDoc working at CMU Robotics Institute. My research interests include: 1. Locomotion robots 2. Semantic and Topological SLAM 3. Spatial based Reinforcement Learning My goal: For robotics
Additional affiliations
June 2019 - June 2021
Carnegie Mellon University
Position
  • PostDoc Position

Publications

Publications (37)
Preprint
Full-text available
We present a method for localizing a single camera with respect to a point cloud map in indoor and outdoor scenes. The problem is challenging because correspondences of local invariant features are inconsistent across the domains between image and 3D. The problem is even more challenging as the method must handle various environmental conditions su...
Preprint
Appearance-based visual localization (AVL) is an approach that aligns the visual image against previously saved target images for robotics navigation. Current visual localization methods are easily affected by viewpoint (forward, backward) and environmental condition (illuminations, weathers) changes, and remains fragile for long-term localization,...
Preprint
Full-text available
Recent years have witnessed the increasing application of place recognition in various environments, such as city roads, large buildings, and a mix of indoor and outdoor places. This task, however, still remains challenging due to the limitations of different sensors and the changing appearance of environments. Current works only consider the use o...
Article
Full-text available
Real-time 3D place recognition is a crucial technology to recover from localization failure in applications like autonomous driving, last-mile delivery, and service robots. However, it is challenging for 3D place retrieval methods to be accurate, efficient, and robust to the variant viewpoints differences. In this paper, we propose FusionVLAD, a fu...
Preprint
Multi-agent exploration of a bounded 3D environment with unknown initial positions of agents is a challenging problem. It requires quickly exploring the environments as well as robustly merging the sub-maps built by the agents. We take the view that the existing approaches are either aggressive or conservative: Aggressive strategies merge two sub-m...
Preprint
The visual camera is an attractive device in beyond visual line of sight (B-VLOS) drone operation, since they are low in size, weight, power, and cost, and can provide redundant modality to GPS failures. However, state-of-the-art visual localization algorithms are unable to match visual data that have a significantly different appearance due to ill...
Preprint
Place recognition is the fundamental module that can assist Simultaneous Localization and Mapping (SLAM) in loop-closure detection and re-localization for long-term navigation. The place recognition community has made astonishing progress over the last $20$ years, and this has attracted widespread research interest and application in multiple field...
Preprint
We present BioSLAM, a lifelong SLAM framework for learning various new appearances incrementally and maintaining accurate place recognition for previously visited areas. Unlike humans, artificial neural networks suffer from catastrophic forgetting and may forget the previously visited areas when trained with new arrivals. For humans, researchers di...
Preprint
We present the ALTO dataset, a vision-focused dataset for the development and benchmarking of Visual Place Recognition and Localization methods for Unmanned Aerial Vehicles. The dataset is composed of two long (approximately 150km and 260km) trajectories flown by a helicopter over Ohio and Pennsylvania, and it includes high precision GPS-INS ground...
Preprint
We present AutoMerge, a LiDAR data processing framework for assembling a large number of map segments into a complete map. Traditional large-scale map merging methods are fragile to incorrect data associations, and are primarily limited to working only offline. AutoMerge utilizes multi-perspective fusion and adaptive loop closure detection for accu...
Preprint
Full-text available
LiDAR-based localization approach is a fundamental module for large-scale navigation tasks, such as last-mile delivery and autonomous driving, and localization robustness highly relies on viewpoints and 3D feature extraction. Our previous work provides a viewpoint-invariant descriptor to deal with viewpoint differences; however, the global descript...
Preprint
Full-text available
For long-term autonomy, most place recognition methods are mainly evaluated on simplified scenarios or simulated datasets, which cannot provide solid evidence to evaluate the readiness for current Simultaneous Localization and Mapping (SLAM). In this paper, we present a long-term place recognition dataset for use in mobile localization under large-...
Article
Traditional manual wheelchairs have a fixed seat with no movement or angle adjustment, which can seriously affect the user's comfort and greatly limit user experience. However, the electric wheelchair relies on strong intelligence and automatic features; it can not only realize the multidegree freedom adjustment of the human body and the seat but a...
Article
Full-text available
Accurate localization on autonomous driving cars is essential for autonomy and driving safety, especially for complex urban streets and search-and-rescue subterranean environments where high-accurate GPS is not available. However current odometry estimation may introduce the drifting problems in long-term navigation without robust global localizati...
Preprint
Full-text available
Accurate localization on autonomous driving cars is essential for autonomy and driving safety, especially for complex urban streets and search-and-rescue subterranean environments where high-accurate GPS is not available. However current odometry estimation may introduce the drifting problems in long-term navigation without robust global localizati...
Article
Full-text available
One of the main obstacles to 3D semantic segmentation is the significant amount of endeavor required to generate expensive point-wise annotations for fully supervised training. To alleviate manual efforts, we propose GIDSeg, a novel approach that can simultaneously learn segmentation from sparse annotations via reasoning global-regional structures...
Preprint
Full-text available
One of the main obstacles to 3D semantic segmentation is the significant amount of endeavor required to generate expensive point-wise annotations for fully supervised training. To alleviate manual efforts, we propose GIDSeg, a novel approach that can simultaneously learn segmentation from sparse annotations via reasoning global-regional structures...
Article
Full-text available
Recognizing the same place under variant viewpoint differences is the fundamental capability for human beings and animals. However, such a strong place recognition ability in robotics is still an unsolved problem. Extracting local invariant descriptors from the same place under various viewpoint differences is difficult. This paper seeks to provide...
Preprint
Full-text available
Acquiring accurate three-dimensional depth information conventionally requires expensive multibeam LiDAR devices. Recently, researchers have developed a less expensive option by predicting depth information from two-dimensional color imagery. However, there still exists a substantial gap in accuracy between depth information estimated from two-dime...
Preprint
Full-text available
Place recognition and loop closure detection are challenging for long-term visual navigation tasks. SeqSLAM is considered to be one of the most successful approaches to achieving long-term localization under varying environmental conditions and changing viewpoints. It depends on a brute-force, time-consuming sequential matching method. We propose M...
Preprint
Full-text available
Visual Place Recognition (VPR) is an important component in both computer vision and robotics applications, thanks to its ability to determine whether a place has been visited and where specifically. A major challenge in VPR is to handle changes of environmental conditions including weather, season and illumination. Most VPR methods try to improve...
Article
Full-text available
Loop Closure Detection (LCD) is the essential module in the simultaneous localization and mapping (SLAM) task. In the current appearance-based SLAM methods, the visual inputs are usually affected by illumination, appearance and viewpoints changes. Comparing to the visual inputs, with the active property, light detection and ranging (LiDAR) based po...
Article
Full-text available
Loop closure detection (LCD) is the key module in appearance based simultaneously localization and mapping (SLAM). However, in the real life, the appearance of visual inputs are usually affected by the illumination changes and texture changes under different weather conditions. Traditional methods in LCD usually rely on handcraft features, however,...
Article
Full-text available
Stable feature extraction is the key for the Loop closure detection (LCD) task in the simultaneously localization and mapping (SLAM) framework. In our paper, the feature extraction is operated by using a generative adversarial networks (GANs) based unsupervised learning. GANs are powerful generative models, however, GANs based adversarial learning...
Conference Paper
Full-text available
Heterogeneous robot introduce a higher perception ability than single type robots in outdoor environments. One key problem is to making the 3D environmental model from the cooperated robots in real time, especially in the unstructured environment. Based on our previous work on outdoor environment registration method, in this paper, we introduce a G...
Article
Full-text available
One of the main applications of mobile robots is the large-scale perception of the outdoor environment. One of the main challenges of this application is fusing environmental data obtained by multiple robots, especially heterogeneous robots. This paper proposes an enhanced iterative closest point (ICP) method for the fast and accurate registration...

Network

Cited By

Projects

Projects (3)
Project
In this project, we propose a 3D framework to combine 3D object detection, tracking with a SLAM framework.
Project
Traditional ICP method and its variants usually have the local minima problem, in this project, we proposed a multi-resolution particle filter based global searching method, which use a coarse-to-fine method to find the best final match.
Project
Enable long-term place recognition under variant conditions.