Artificial Intelligence and Robotics Commons^™

Obstacle Avoidance Path Planning And Simulation Of Mobile Picking Robot Based On Dppo, Junqiang Lin, Hongjun Wang, Xiangjun Zou, Po Zhang, Chengen Li, Yipeng Zhou, Shujie Yao

Journal of System Simulation

Abstract: Aiming at the autonomous decision-making difficulty of mobile picking robots in random and changeable complicated path environment during field operations, an autonomous obstacle avoidance path planning method based on deep reinforcement learning is propose. By setting the state space and action space and using the artificial potential field method to design the reward function, an obstacle penalty coefficient setting method based on collision cone collision avoidance detection is proposed to improve the autonomous collision avoidance ability. A virtual simulation system is constructed, in which the learning and training of the mobile picking robot is carried out and verified by …

Intelligent Path Planning For Mobile Robots Based On Sac Algorithm, Laiyi Yang, Jing Bi, Haitao Yuan

Journal of System Simulation

Abstract: Aiming at the high dimension, slow convergence and complex modelling of traditional path planning algorithms for mobile robots, a new intelligent path planning algorithm is proposed, which is based on deep reinforcement learning soft actor-critic (SAC) algorithm to save the poor performance of robot in complicated environments with static and dynamic obstacles. An improved reward function is designed to enable mobile robots to quickly avoid obstacles and reach targets by using state dynamic normalization and priority experience pool techniques. To evaluate the performance, a pygame-based simulation environment is constructed. Compared with proximal policy optimization(PPO) algorithm, experimental …

Intelligent Air Defense Task Assignment Based On Assignment Strategy Optimization Algorithm, Jiayi Liu, Gang Wang, Qiang Fu, Xiangke Guo, Siyuan Wang

Journal of System Simulation

Abstract: Aiming at the insufficient solving speed of assignment strategy optimization algorithm in largescale scenarios, deep reinforcement learning is combined with Markov decision process to carry out the intelligent large-scale air defense task assignment. According to the characteristics of large-scale air defense operations, Markov decision process is used to model the agent and a digital battlefield simulation environment is built. Air defense task assignment agent is designed and trained in digital battlefield simulation environment through proximal policy optimization algorithm. The feasibility and advantage of the method are verified by taking a large-scale ground-to-air countermeasure mission as an example.

Real-Time Simulation Method Of Ultra-High-Definition Video Texture, Yangyang Liu, Gangyi Ding, Dapeng Yan, Tong Xue

Journal of System Simulation

Abstract: With the development and promotion of ultra-high-definition video technology, how to quickly simulate ultra-high-definition video texture has gradually become an important research issue. Aiming at the completeness and high efficiency of simulation, a real-time simulation method of ultra-high-definition video texture is proposed to improve the video texture quality and display frequency simultaneously. A fast generation method of video texture based on GPU parallel is designed, which solves the time-consuming problem of decoding and transcoding. An efficient data transmission method based on shared texture is proposed. On the basis of the simulation engine, the real-time simulation system of ultra-high-definition video …

Research On Nested Named Entity Recognition In Missile Field Text, Jingwen Guan, Xiao Song, Xiaoqing Li, Tong Yang, Junhua Zhou

Journal of System Simulation

Abstract: Compared with the text recognition in conventional fields, it is difficult to recognize the large number of nested named entities in professional terms. This is also one of the care challenges in building the knowledge graph in aerospace field. For the named entity recognition technologies, bidirectional long short-term memory network plus conditional random field (BiLSTM-CRF) is often used to identify entities, which is difficult to distinguish the complex relationships such as nesting and intersection of terms in missile field. In order to solve the problem, based on the nested entity labeling of domain text, a nested named entity recognition …

Robot Path Planning By Fusing Particle Swarm Algorithm And Improved Grey Wolf Algorithm, Menglong Cao, Wenbin Zhao, Zhiqiang Chen

Journal of System Simulation

Abstract: Aiming at the long paths and slow convergence speed of GWO algorithm in robot path planning, a hybrid PSO-GWO algorithm based on PSO algorithm and the improved GWO algorithm is proposed. By running PSO algorithm for many times, the initial wolf group size and initial fitness value are determined. A nonlinear convergence factor is introduced to balance the exploration and development capabilities of GWO algorithm, and a dynamic inertia weight factor is proposed to ensure the leadership system of alpha wolf and to promote the population communication. Levy flight and greedy strategy are used to effectively avoid the local …

Monitoring Method Research On Passenger Behavior On Escalator Based On Digital Twin, Nan Lü, Qibing Wang, Lu Jiawei, Juntong Chen, Gang Xiao

Journal of System Simulation

Abstract: In order to solve the problems that the traditional escalator cannot be monitored and analyzed in real time during operation, the management and maintenance only on escalator equipment side, and the lack of monitoring passenger dangerous behavior, a monitoring method of passenger behavior on escalator based on digital twin is proposed. By constructing the digital twin of escalators, a visual interface is designed to map the escalator running status and passenger behavior data. Through passenger video surveillance, the improved OpenPose posture recognition algorithm is used to obtain the key point data of human body. Posture recognition is classified to …

A Compliant Robot Control Based On Extended Social-Force Model For Human-Following And Obstacle Avoidance, Jianwei Peng, Zhelin Liao, Hanchen Yao, Zhiyu Wan, Liqi Zhu, Houde Dai

Journal of System Simulation

Abstract: Human-robot coexisting is an essential feature of the next generation mobile robot. A compliant robot control strategy based on the extended social-force model for human-following and obstacle avoidance in coexisting-cooperative-cognitive environment is presented. The human-following controller based on impedance control can simultaneously adjust human-robot interaction force and position deviation to carry out the compliant human-following of mobile robots. Considering humanrobot- obstacle interactions, based on the extended social-force model and proxemics, a control strategy for human-friendly compliant human-following and obstacle avoidance is designed to solve the obstacle avoidance problem of robot and ensure the human comfort and improving the social …

Machine Learning-Based Classification Of Chronic Traumatic Brain Injury Using Hybrid Diffusion Imaging, Jennifer Muller, Ruixuan Wang, Devon Middleton, Mahdi Alizadeh, Kichang Kang, Ryan Hryczyk, George Zabrecky, Chloe Hriso, Emily Navarreto, Nancy Wintering, Anthony J. Bazzan, Chengyuan Wu, Daniel A. Monti, Xun Jiao, Qianhong Wu, Andrew B. Newberg, Feroze Mohamed

Marcus Institute of Integrative Health Faculty Papers

BACKGROUND AND PURPOSE: Traumatic brain injury (TBI) can cause progressive neuropathology that leads to chronic impairments, creating a need for biomarkers to detect and monitor this condition to improve outcomes. This study aimed to analyze the ability of data-driven analysis of diffusion tensor imaging (DTI) and neurite orientation dispersion imaging (NODDI) to develop biomarkers to infer symptom severity and determine whether they outperform conventional T1-weighted imaging.

MATERIALS AND METHODS: A machine learning-based model was developed using a dataset of hybrid diffusion imaging of patients with chronic traumatic brain injury. We first extracted the useful features from the hybrid diffusion imaging …

Dynamic Graph Enhanced Contrastive Learning For Chest X-Ray Report Generation, Mingjie Li, Bingqian Lin, Zicong Chen, Haokun Lin, Xiaodan Liang, Xiaojun Chang

Computer Vision Faculty Publications

Automatic radiology reporting has great clinical potential to relieve radiologists from heavy workloads and improve diagnosis interpretation. Recently, researchers have enhanced data-driven neural networks with medical knowledge graphs to eliminate the severe visual and textual bias in this task. The structures of such graphs are exploited by using the clinical dependencies formed by the disease topic tags via general knowledge and usually do not update during the training process. Consequently, the fixed graphs can not guarantee the most appropriate scope of knowledge and limit the effectiveness. To address the limitation, we propose a knowledge graph with Dynamic structure and nodes …

3d Semantic Segmentation In The Wild: Learning Generalized Models For Adverse-Condition Point Clouds, Aoran Xiao, Jiaxing Huang, Weihao Xuan, Ruijie Ren, Kangcheng Liu, Dayan Guan, Abdulmotaleb El Saddik, Shijian Lu, Eric Xing

Computer Vision Faculty Publications

Robust point cloud parsing under all-weather conditions is crucial to level-5 autonomy in autonomous driving. However, how to learn a universal 3D semantic segmentation (3DSS) model is largely neglected as most existing benchmarks are dominated by point clouds captured under normal weather. We introduce SemanticSTF, an adverse-weather point cloud dataset that provides dense point-level annotations and allows to study 3DSS under various adverse weather conditions. We study all-weather 3DSS modeling under two setups: 1) domain adaptive 3DSS that adapts from normal-weather data to adverse-weather data; 2) domain generalizable 3DSS that learns all-weather 3DSS models from normal-weather data. Our studies reveal …

3d-Aware Multi-Class Image-To-Image Translation With Nerfs, Senmao Li, Joost Van De Weijer, Yaxing Wang, Fahad Shahbaz Khan, Meiqin Liu, Jian Yang

Computer Vision Faculty Publications

Recent advances in 3D-aware generative models (3D-aware GANs) combined with Neural Radiance Fields (NeRF) have achieved impressive results. However no prior works investigate 3D-aware GANs for 3D consistent multiclass image-to-image (3D-aware 121) translation. Naively using 2D-121 translation methods suffers from unrealistic shape/identity change. To perform 3D-aware multiclass 121 translation, we decouple this learning process into a multiclass 3D-aware GAN step and a 3D-aware 121 translation step. In the first step, we propose two novel techniques: a new conditional architecture and an effective training strategy. In the second step, based on the well-trained multiclass 3D-aware GAN architecture, that preserves view-consistency, we …

Discriminative Co-Saliency And Background Mining Transformer For Co-Salient Object Detection, Long Li, Junwei Han, Ni Zhang, Nian Liu, Salman Khan, Hisham Cholakkal, Rao Muhammad Anwer, Fahad Shahbaz Khan

Computer Vision Faculty Publications

Most previous co-salient object detection works mainly focus on extracting co-salient cues via mining the consistency relations across images while ignore explicit exploration of background regions. In this paper, we propose a Discriminative co-saliency and background Mining Transformer framework (DMT) based on several economical multi-grained correlation modules to explicitly mine both co-saliency and background information and effectively model their discrimination. Specifically, we first propose a region-to-region correlation module for introducing inter-image relations to pixel-wise segmentation features while maintaining computational efficiency. Then, we use two types of pre-defined tokens to mine co-saliency and background information via our proposed contrast-induced pixel-to-token correlation …

Burstormer: Burst Image Restoration And Enhancement Transformer, Akshay Dudhane, Syed Waqas Zamir, Salman Khan, Fahad Shahbaz Khan, Ming Hsuan Yang

Computer Vision Faculty Publications

On a shutter press, modern handheld cameras capture multiple images in rapid succession and merge them to generate a single image. However, individual frames in a burst are misaligned due to inevitable motions and contain multiple degradations. The challenge is to properly align the successive image shots and merge their complementary information to achieve high-quality outputs. Towards this direction, we propose Burstormer: a novel transformer-based architecture for burst image restoration and enhancement. In comparison to existing works, our approach exploits multi-scale local and non-local features to achieve improved alignment and feature fusion. Our key idea is to enable inter-frame communication …

Clip2protect: Protecting Facial Privacy Using Text-Guided Makeup Via Adversarial Latent Search, Fahad Shamshad, Muzammal Naseer, Karthik Nandakumar

Computer Vision Faculty Publications

The success of deep learning based face recognition systems has given rise to serious privacy concerns due to their ability to enable unauthorized tracking of users in the digital world. Existing methods for enhancing privacy fail to generate 'naturalistic' images that can protect facial privacy without compromising user experience. We propose a novel two-step approach for facial privacy protection that relies on finding adversarial latent codes in the low- dimensional manifold of a pretrained generative model. The first step inverts the given face image into the latent space and finetunes the generative model to achieve an accurate reconstruction of the …

Multiclass Confidence And Localization Calibration For Object Detection, Bimsara Pathiraja, Malitha Gunawardhana, Muhammad Haris Khan

Computer Vision Faculty Publications

Albeit achieving high predictive accuracy across many challenging computer vision problems, recent studies suggest that deep neural networks (DNNs) tend to make over-confident predictions, rendering them poorly calibrated. Most of the existing attempts for improving DNN calibration are limited to classification tasks and restricted to calibrating in-domain predictions. Surprisingly, very little to no attempts have been made in studying the calibration of object detection methods, which occupy a pivotal space in vision-based security-sensitive, and safety-critical applications. In this paper, we propose a new train-time technique for calibrating modern object detection methods. It is capable of jointly calibrating multiclass confidence and …

N-Shot Benchmarking Of Whisper On Diverse Arabic Speech Recognition, Bashar Talafha, Abdul Waheed, Muhammad Abdul-Mageed

Natural Language Processing Faculty Publications

Whisper, the recently developed multilingual weakly supervised model, is reported to perform well on multiple speech recognition benchmarks in both monolingual and multilingual settings. However, it is not clear how Whisper would fare under diverse conditions even on languages it was evaluated on such as Arabic. In this work, we address this gap by comprehensively evaluating Whisper on several varieties of Arabic speech for the ASR task. Our evaluation covers most publicly available Arabic speech data and is performed under n-shot (zero-, few-, and full) finetuning. We also investigate the robustness of Whisper under completely novel conditions, such as in …

Impact Analysis Of Gpt Technology Revolution On Fundamental Scientific Research, Mengge Sun, Tao Han, Yanpeng Wang, Yuxin Huang, Xiwen Liu

Bulletin of Chinese Academy of Sciences (Chinese Version)

The generative large model GPT represented by ChatGPT is developing rapidly, which has aroused extensive discussion in academic circle and the industry and has an incalculable impact on foundational scientific research development. The study first sorts out the development of the GPT technological revolution, and discusses the new changes brought about by this technology in scientific research. Then, based on the three aspects of application status, core principles and innovation subjects, the impact of the GPT technological revolution on basic scientific research and its development suggestions for China are discussed. The study believes that GPT technology can certainly play a …

Vision Language Navigation With Knowledge-Driven Environmental Dreamer, Fengda Zhu, Vincent C.S. Lee, Xiaojun Chang, Xiaodan Liang

Computer Vision Faculty Publications

Vision-language navigation (VLN) requires an agent to perceive visual observation in a house scene and navigate step-by-step following natural language instruction. Due to the high cost of data annotation and data collection, current VLN datasets provide limited instruction-trajectory data samples. Learning vision-language alignment for VLN from limited data is challenging since visual observation and language instruction are both complex and diverse. Previous works only generate augmented data based on original scenes while failing to generate data samples from unseen scenes, which limits the generalization ability of the navigation agent. In this paper, we introduce the Knowledge-driven Environmental Dreamer (KED), a …

Threads, Buckets, And Impact: A Framework For Tool Accelerated Machine Learning Courses, Jonathan Adam Niemirowski

Doctoral Dissertations

Artificial intelligence and machine learning (ML) have exploded in use, accessibility, and awareness in the past few years, particularly with the release of ChatGPT in late 2022. Advances in end-user ML tools are accelerating the development of ML applications, lowering the technical barrier of entry for users outside of the computer science (CS) community. Access to ML education within STEM is mostly limited to upper-level computer science courses that have deep pre-requisite requirements or to introductory workshops that yield limited ML skills. Despite the critical need for ML education, there is a lack of guidance in instructional design for applied …