Alert button
Picture for Hao Yin

Hao Yin

Alert button

Ground-Challenge: A Multi-sensor SLAM Dataset Focusing on Corner Cases for Ground Robots

Jul 08, 2023
Jie Yin, Hao Yin, Conghui Liang, Zhengyou Zhang

Figure 1 for Ground-Challenge: A Multi-sensor SLAM Dataset Focusing on Corner Cases for Ground Robots
Figure 2 for Ground-Challenge: A Multi-sensor SLAM Dataset Focusing on Corner Cases for Ground Robots
Figure 3 for Ground-Challenge: A Multi-sensor SLAM Dataset Focusing on Corner Cases for Ground Robots
Figure 4 for Ground-Challenge: A Multi-sensor SLAM Dataset Focusing on Corner Cases for Ground Robots

High-quality datasets can speed up breakthroughs and reveal potential developing directions in SLAM research. To support the research on corner cases of visual SLAM systems, this paper presents Ground-Challenge: a challenging dataset comprising 36 trajectories with diverse corner cases such as aggressive motion, severe occlusion, changing illumination, few textures, pure rotation, motion blur, wheel suspension, etc. The dataset was collected by a ground robot with multiple sensors including an RGB-D camera, an inertial measurement unit (IMU), a wheel odometer and a 3D LiDAR. All of these sensors were well-calibrated and synchronized, and their data were recorded simultaneously. To evaluate the performance of cutting-edge SLAM systems, we tested them on our dataset and demonstrated that these systems are prone to drift and fail on specific sequences. We will release the full dataset and relevant materials upon paper publication to benefit the research community. For more information, visit our project website at https://github.com/sjtuyinjie/Ground-Challenge.

Viaarxiv icon

Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackers

May 10, 2023
Lei Yuan, Zi-Qian Zhang, Ke Xue, Hao Yin, Feng Chen, Cong Guan, Li-He Li, Chao Qian, Yang Yu

Figure 1 for Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackers
Figure 2 for Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackers
Figure 3 for Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackers
Figure 4 for Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackers

Cooperative multi-agent reinforcement learning (CMARL) has shown to be promising for many real-world applications. Previous works mainly focus on improving coordination ability via solving MARL-specific challenges (e.g., non-stationarity, credit assignment, scalability), but ignore the policy perturbation issue when testing in a different environment. This issue hasn't been considered in problem formulation or efficient algorithm design. To address this issue, we firstly model the problem as a limited policy adversary Dec-POMDP (LPA-Dec-POMDP), where some coordinators from a team might accidentally and unpredictably encounter a limited number of malicious action attacks, but the regular coordinators still strive for the intended goal. Then, we propose Robust Multi-Agent Coordination via Evolutionary Generation of Auxiliary Adversarial Attackers (ROMANCE), which enables the trained policy to encounter diversified and strong auxiliary adversarial attacks during training, thus achieving high robustness under various policy perturbations. Concretely, to avoid the ego-system overfitting to a specific attacker, we maintain a set of attackers, which is optimized to guarantee the attackers high attacking quality and behavior diversity. The goal of quality is to minimize the ego-system coordination effect, and a novel diversity regularizer based on sparse action is applied to diversify the behaviors among attackers. The ego-system is then paired with a population of attackers selected from the maintained attacker set, and alternately trained against the constantly evolving attackers. Extensive experiments on multiple scenarios from SMAC indicate our ROMANCE provides comparable or better robustness and generalization ability than other baselines.

* In: Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI'23), 2023 
Viaarxiv icon

Sky-GVINS: a Sky-segmentation Aided GNSS-Visual-Inertial System for Robust Navigation in Urban Canyons

Apr 08, 2023
Jie Yin, Tao Li, Hao Yin, Wenxian Yu, Danping Zou

Figure 1 for Sky-GVINS: a Sky-segmentation Aided GNSS-Visual-Inertial System for Robust Navigation in Urban Canyons
Figure 2 for Sky-GVINS: a Sky-segmentation Aided GNSS-Visual-Inertial System for Robust Navigation in Urban Canyons
Figure 3 for Sky-GVINS: a Sky-segmentation Aided GNSS-Visual-Inertial System for Robust Navigation in Urban Canyons
Figure 4 for Sky-GVINS: a Sky-segmentation Aided GNSS-Visual-Inertial System for Robust Navigation in Urban Canyons

Integrating Global Navigation Satellite Systems (GNSS) in Simultaneous Localization and Mapping (SLAM) systems draws increasing attention to a global and continuous localization solution. Nonetheless, in dense urban environments, GNSS-based SLAM systems will suffer from the Non-Line-Of-Sight (NLOS) measurements, which might lead to a sharp deterioration in localization results. In this paper, we propose to detect the sky area from the up-looking camera to improve GNSS measurement reliability for more accurate position estimation. We present Sky-GVINS: a sky-aware GNSS-Visual-Inertial system based on a recent work called GVINS. Specifically, we adopt a global threshold method to segment the sky regions and non-sky regions in the fish-eye sky-pointing image and then project satellites to the image using the geometric relationship between satellites and the camera. After that, we reject satellites in non-sky regions to eliminate NLOS signals. We investigated various segmentation algorithms for sky detection and found that the Otsu algorithm reported the highest classification rate and computational efficiency, despite the algorithm's simplicity and ease of implementation. To evaluate the effectiveness of Sky-GVINS, we built a ground robot and conducted extensive real-world experiments on campus. Experimental results show that our method improves localization accuracy in both open areas and dense urban environments compared to the baseline method. Finally, we also conduct a detailed analysis and point out possible further directions for future research. For detailed information, visit our project website at https://github.com/SJTU-ViSYS/Sky-GVINS.

Viaarxiv icon

A multi view multi stage and multi window framework for pulmonary artery segmentation from CT scans

Sep 14, 2022
ZeYu Liu, Yi Wang, Jing Wen, Yong Zhang, Hao Yin, Chao Guo, ZhongYu Wang

Figure 1 for A multi view multi stage and multi window framework for pulmonary artery segmentation from CT scans
Figure 2 for A multi view multi stage and multi window framework for pulmonary artery segmentation from CT scans
Figure 3 for A multi view multi stage and multi window framework for pulmonary artery segmentation from CT scans
Figure 4 for A multi view multi stage and multi window framework for pulmonary artery segmentation from CT scans

This is the technical report of the 9th place in the final result of PARSE2022 Challenge. We solve the segmentation problem of the pulmonary artery by using a two-stage method based on a 3D CNN network. The coarse model is used to locate the ROI, and the fine model is used to refine the segmentation result. In addition, in order to improve the segmentation performance, we adopt multi-view and multi-window level method, at the same time we employ a fine-tune strategy to mitigate the impact of inconsistent labeling.

Viaarxiv icon

Model Generation with Provable Coverability for Offline Reinforcement Learning

Jun 08, 2022
Chengxing Jia, Hao Yin, Chenxiao Gao, Tian Xu, Lei Yuan, Zongzhang Zhang, Yang Yu

Figure 1 for Model Generation with Provable Coverability for Offline Reinforcement Learning
Figure 2 for Model Generation with Provable Coverability for Offline Reinforcement Learning
Figure 3 for Model Generation with Provable Coverability for Offline Reinforcement Learning
Figure 4 for Model Generation with Provable Coverability for Offline Reinforcement Learning

Model-based offline optimization with dynamics-aware policy provides a new perspective for policy learning and out-of-distribution generalization, where the learned policy could adapt to different dynamics enumerated at the training stage. But due to the limitation under the offline setting, the learned model could not mimic real dynamics well enough to support reliable out-of-distribution exploration, which still hinders policy to generalize well. To narrow the gap, previous works roughly ensemble randomly initialized models to better approximate the real dynamics. However, such practice is costly and inefficient, and provides no guarantee on how well the real dynamics could be approximated by the learned models, which we name coverability in this paper. We actively address this issue by generating models with provable ability to cover real dynamics in an efficient and controllable way. To that end, we design a distance metric for dynamic models based on the occupancy of policies under the dynamics, and propose an algorithm to generate models optimizing their coverage for the real dynamics. We give a theoretical analysis on the model generation process and proves that our algorithm could provide enhanced coverability. As a downstream task, we train a dynamics-aware policy with minor or no conservative penalty, and experiments demonstrate that our algorithm outperforms prior offline methods on existing offline RL benchmarks. We also discover that policies learned by our method have better zero-shot transfer performance, implying their better generalization.

* Released without the permission of all co-authors 
Viaarxiv icon

Angle Estimation for Terahertz Ultra-Massive MIMO-Based Space-to-Air Communications

Aug 02, 2021
Anwen Liao, Zhen Gao, Yang Yang, Ha H. Nguyen, Hua Wang, Hao Yin

Figure 1 for Angle Estimation for Terahertz Ultra-Massive MIMO-Based Space-to-Air Communications
Figure 2 for Angle Estimation for Terahertz Ultra-Massive MIMO-Based Space-to-Air Communications
Figure 3 for Angle Estimation for Terahertz Ultra-Massive MIMO-Based Space-to-Air Communications
Figure 4 for Angle Estimation for Terahertz Ultra-Massive MIMO-Based Space-to-Air Communications

This paper investigates terahertz ultra-massive (UM)-MIMO-based angle estimation for space-to-air communications, which can solve the performance degradation problem caused by the dual delay-beam squint effects of terahertz UM-MIMO channels. Specifically, we first design a grouping true-time delay unit module that can significantly mitigate the impact of delay-beam squint effects to establish the space-to-air THz link. Based on the subarray selection scheme, the UM hybrid array can be equivalently considered as a low-dimensional fully-digital array, and then the fine estimates of azimuth/elevation angles at both UAVs and satellite can be separately acquired using the proposed prior-aided iterative angle estimation algorithm. The simulation results that close to Cram\'{e}r-Rao lower bounds verify the effectiveness of our solution.

* Accepted by IEEE/CIC International Conference on Communications in China. arXiv admin note: text overlap with arXiv:2103.01829 
Viaarxiv icon

Terahertz Ultra-Massive MIMO-Based Aeronautical Communications in Space-Air-Ground Integrated Networks

Mar 03, 2021
Anwen Liao, Zhen Gao, Dongming Wang, Hua Wang, Hao Yin, Derrick Wing Kwan Ng, Mohamed-Slim Alouini

Figure 1 for Terahertz Ultra-Massive MIMO-Based Aeronautical Communications in Space-Air-Ground Integrated Networks
Figure 2 for Terahertz Ultra-Massive MIMO-Based Aeronautical Communications in Space-Air-Ground Integrated Networks
Figure 3 for Terahertz Ultra-Massive MIMO-Based Aeronautical Communications in Space-Air-Ground Integrated Networks
Figure 4 for Terahertz Ultra-Massive MIMO-Based Aeronautical Communications in Space-Air-Ground Integrated Networks

The emerging space-air-ground integrated network has attracted intensive research and necessitates reliable and efficient aeronautical communications. This paper investigates terahertz Ultra-Massive (UM)-MIMO-based aeronautical communications and proposes an effective channel estimation and tracking scheme, which can solve the performance degradation problem caused by the unique {\emph{triple delay-beam-Doppler squint effects}} of aeronautical terahertz UM-MIMO channels. Specifically, based on the rough angle estimates acquired from navigation information, an initial aeronautical link is established, where the delay-beam squint at transceiver can be significantly mitigated by employing a Grouping True-Time Delay Unit (GTTDU) module (e.g., the designed {\emph{Rotman lens}}-based GTTDU module). According to the proposed prior-aided iterative angle estimation algorithm, azimuth/elevation angles can be estimated, and these angles are adopted to achieve precise beam-alignment and refine GTTDU module for further eliminating delay-beam squint. Doppler shifts can be subsequently estimated using the proposed prior-aided iterative Doppler shift estimation algorithm. On this basis, path delays and channel gains can be estimated accurately, where the Doppler squint can be effectively attenuated via compensation process. For data transmission, a data-aided decision-directed based channel tracking algorithm is developed to track the beam-aligned effective channels. When the data-aided channel tracking is invalid, angles will be re-estimated at the pilot-aided channel tracking stage with an equivalent sparse digital array, where angle ambiguity can be resolved based on the previously estimated angles. The simulation results and the derived Cram\'{e}r-Rao lower bounds verify the effectiveness of our solution.

* 26 pages, 20 figures, accepted by IEEE Journal on Selected Areas in Communications 
Viaarxiv icon

Higher-order clustering in networks

Jan 05, 2018
Hao Yin, Austin R. Benson, Jure Leskovec

Figure 1 for Higher-order clustering in networks
Figure 2 for Higher-order clustering in networks
Figure 3 for Higher-order clustering in networks
Figure 4 for Higher-order clustering in networks

A fundamental property of complex networks is the tendency for edges to cluster. The extent of the clustering is typically quantified by the clustering coefficient, which is the probability that a length-2 path is closed, i.e., induces a triangle in the network. However, higher-order cliques beyond triangles are crucial to understanding complex networks, and the clustering behavior with respect to such higher-order network structures is not well understood. Here we introduce higher-order clustering coefficients that measure the closure probability of higher-order network cliques and provide a more comprehensive view of how the edges of complex networks cluster. Our higher-order clustering coefficients are a natural generalization of the traditional clustering coefficient. We derive several properties about higher-order clustering coefficients and analyze them under common random graph models. Finally, we use higher-order clustering coefficients to gain new insights into the structure of real-world networks from several domains.

* Phys. Rev. E 97, 052306 (2018)  
Viaarxiv icon