It was shown in our earlier work that the measurement error in the microphone position affected the room impulse response (RIR) which in turn affected the single-channel close microphone and multi-channel distant microphone speech recognition. In this paper, as an extension, we systematically study to identify the optimal location of the microphone, given an approximate and hence erroneous location of the microphone in 3D space. The primary idea is to use Monte-Carlo technique to generate a large number of random microphone positions around the erroneous microphone position and select the microphone position that results in the best performance of a general purpose automatic speech recognition (gp-asr). We experiment with clean and noisy speech and show that the optimal location of the microphone is unique and is affected by noise.
Recent localization frameworks exploit spatial information of complex channel measurements (CMs) to estimate accurate positions even in multipath propagation scenarios. State-of-the art CM fingerprinting(FP)-based methods employ convolutional neural networks (CNN) to extract the spatial information. However, they need spatially dense data sets (associated with high acquisition and maintenance efforts) to work well -- which is rarely the case in practical applications. If such data is not available (or its quality is low), we cannot compensate the performance degradation of CNN-based FP as they do not provide statistical position estimates, which prevents a fusion with other sources of information on the observation level. We propose a novel localization framework that adapts well to sparse datasets that only contain CMs of specific areas within the environment with strong multipath propagation. Our framework compresses CMs into informative features to unravel spatial information. It then regresses Gaussian processes (GPs) for each of them, which imply statistical observation models based on distance-dependent covariance kernels. Our framework combines the trained GPs with line-of-sight ranges and a dynamics model in a particle filter. Our measurements show that our approach outperforms state-of-the-art CNN fingerprinting (0.52 m vs. 1.3 m MAE) on spatially sparse data collected in a realistic industrial indoor environment.
In this paper new hierarchical hybrid fuzzy-crisp methods for decision making and action selection of an agent in soccer simulation 3D environment are presented. First, the skills of an agent are introduced, implemented and classified in two layers, the basicskills and the highlevel skills. In the second layer, a twophase mechanism for decision making is introduced. In phase one, some useful methods are implemented which check the agent's situation for performing required skills. In the next phase, the team str ategy, team for mation, agent's role and the agent's positioning system are introduced. A fuzzy logical approach is employed to recognize the team strategy and further more to tell the player the best position to move. At last, we comprised our implemented algor ithm in the Robocup Soccer Simulation 3D environment and results showed th eefficiency of the introduced methodology.
Contour tracking plays a crucial role in multi-axis motion control systems, and it requires both multi-axial contouring as well as standard servo performance in each axis. Among the existing contouring control methods, the cross coupled control (CCC) lacks of an asymptotical tracking performance for general contours, and the task coordinate frame (TCF) control usually leads to system nonlinearity, and by design is not well-suited for multi-axis contour tracking. Here we propose a novel time-varying internal model principle-based contouring control (TV-IMCC) methodology to enhance contour tracking performance with both axial and contour error reduction. The proposed TV-IMCC is twofold, including an extended position domain framework with master-slave structures for contour regulation, and a time-varying internal model principle-based controller for each axial tracking precision improvement. Specifically, a novel signal conversion algorithm is proposed with the extended position domain framework, hence the original n-axis contouring problem can be decoupled into (n-1) two-axis master-slave tracking problems in the position domain, and the class of contour candidates can be extended as well. With this, the time-varying internal model principle-based control method is proposed to deal with the time-varying dynamics in the axial systems resulted from the transformation between the time and position domains. Furthermore, the stability analysis is provided for the closed-loop system of the TV-IMCC. Various simulation and experimental results validate the TV-IMCC with enhanced contour tracking performance compared with the existing methods. Moreover, there is no strict requirement on the precision of the master axis, therefore a potential application of the TV-IMCC is multi-axis macro-micro motion systems.
Trust is often cited as an essential criterion for the effective use and real-world deployment of AI. Researchers argue that AI should be more transparent to increase trust, making transparency one of the main goals of XAI. Nevertheless, empirical research on this topic is inconclusive regarding the effect of transparency on trust. An explanation for this ambiguity could be that trust is operationalized differently within XAI. In this position paper, we advocate for a clear distinction between behavioral (objective) measures of reliance and attitudinal (subjective) measures of trust. However, researchers sometimes appear to use behavioral measures when intending to capture trust, although attitudinal measures would be more appropriate. Based on past research, we emphasize that there are sound theoretical reasons to keep trust and reliance separate. Properly distinguishing these two concepts provides a more comprehensive understanding of how transparency affects trust and reliance, benefiting future XAI research.
Recently, lane detection has made great progress in autonomous driving. RESA (REcurrent Feature-Shift Aggregator) is based on image segmentation. It presents a novel module to enrich lane feature after preliminary feature extraction with an ordinary CNN. For Tusimple dataset, there is not too complicated scene and lane has more prominent spatial features. On the basis of RESA, we introduce the method of position embedding to enhance the spatial features. The experimental results show that this method has achieved the best accuracy 96.93% on Tusimple dataset.
Artificial intelligence (AI) has been embedded into many aspects of people's daily lives and it has become normal for people to have AI make decisions for them. Reinforcement learning (RL) models increase the space of solvable problems with respect to other machine learning paradigms. Some of the most interesting applications are in situations with non-differentiable expected reward function, operating in unknown or underdefined environment, as well as for algorithmic discovery that surpasses performance of any teacher, whereby agent learns from experimental experience through simple feedback. The range of applications and their social impact is vast, just to name a few: genomics, game-playing (chess, Go, etc.), general optimization, financial investment, governmental policies, self-driving cars, recommendation systems, etc. It is therefore essential to improve the trust and transparency of RL-based systems through explanations. Most articles dealing with explainability in artificial intelligence provide methods that concern supervised learning and there are very few articles dealing with this in the area of RL. The reasons for this are the credit assignment problem, delayed rewards, and the inability to assume that data is independently and identically distributed (i.i.d.). This position paper attempts to give a systematic overview of existing methods in the explainable RL area and propose a novel unified taxonomy, building and expanding on the existing ones. The position section describes pragmatic aspects of how explainability can be observed. The gap between the parties receiving and generating the explanation is especially emphasized. To reduce the gap and achieve honesty and truthfulness of explanations, we set up three pillars: proactivity, risk attitudes, and epistemological constraints. To this end, we illustrate our proposal on simple variants of the shortest path problem.
Mission planners for aircraft operating under threat of detection from ground-based radar systems are often concerned with the probability of detection. Current approaches to path planning in such environments consider the radar state (i.e. radar position and parameters) to be deterministic and known. In practice, there is uncertainty in the radar state which induces uncertainty in the probability of detection. This paper presents a method to incorporate the uncertainty of the radar state in a single-pulse radar detection model. The method linearizes the radar detection model with respect to the the radar state and uses the linearized models to estimate, to the first order, the variance of the probability of detection. The results in this paper validate the linearization using Monte Carlo analysis and illustrate the sensitivity of the probability of detection to radar state uncertainty.
The dual-function radar communication (DFRC) is an essential technology in Internet of Vehicles (IoV). Consider that the road-side unit (RSU) employs the DFRC signals to sense the vehicles' position state information (PSI), and communicates with the vehicles based on PSI. The objective of this paper is to minimize the maximum communication delay among all vehicles by considering the estimation accuracy constraint of the vehicles' PSI and the transmit power constraint of RSU. By leveraging convex optimization theory, two iterative power allocation algorithms are proposed with different complexities and applicable scenarios. Simulation results indicate that the proposed power allocation algorithm converges and can significantly reduce the maximum transmit delay among vehicles compared with other schemes.
The conventional direction of arrival (DOA) estimation methods are performed with multiple receiving channels. In this paper, a changeling DOA estimation problem is addressed in a different scenario with only one full-functional receiving channel. A new unmanned aerial vehicle (UAV) swarm system using multiple lifted reconfigurable intelligent surface (RIS) is proposed for the DOA estimation. The UAV movement degrades the DOA estimation performance significantly, and the existing atomic norm minimization (ANM) methods cannot be used in the scenario with array perturbation. Specifically, considering the position perturbation of UAVs, a new atomic norm-based DOA estimation method is proposed, where an atomic norm is defined with the parameter of the position perturbation. Then, a customized semi-definite programming (SDP) method is derived to solve the atomic norm-based method, where different from the traditional SDP method, an additional transforming matrix is formulated. Moreover, a gradient descent method is applied to refine the estimated DOA and the position perturbation further. Simulation results show that the proposed method achieves much better DOA estimation performance in the RIS-aided UAV swarm system with only one receiving channel than various benchmark schemes.
Recent studies have shown that language models pretrained and/or fine-tuned on randomly permuted sentences exhibit competitive performance on GLUE, putting into question the importance of word order information. Somewhat counter-intuitively, some of these studies also report that position embeddings appear to be crucial for models' good performance with shuffled text. We probe these language models for word order information and investigate what position embeddings learned from shuffled text encode, showing that these models retain information pertaining to the original, naturalistic word order. We show this is in part due to a subtlety in how shuffling is implemented in previous work -- before rather than after subword segmentation. Surprisingly, we find even Language models trained on text shuffled after subword segmentation retain some semblance of information about word order because of the statistical dependencies between sentence length and unigram probabilities. Finally, we show that beyond GLUE, a variety of language understanding tasks do require word order information, often to an extent that cannot be learned through fine-tuning.
We investigate what kind of structural knowledge learned in neural network encoders is transferable to processing natural language. We design artificial languages with structural properties that mimic natural language, pretrain encoders on the data, and see how much performance the encoder exhibits on downstream tasks in natural language. Our experimental results show that pretraining with an artificial language with a nesting dependency structure provides some knowledge transferable to natural language. A follow-up probing analysis indicates that its success in the transfer is related to the amount of encoded contextual information and what is transferred is the knowledge of position-aware context dependence of language. Our results provide insights into how neural network encoders process human languages and the source of cross-lingual transferability of recent multilingual language models.
Transformer-based language models usually treat texts as linear sequences. However, most texts also have an inherent hierarchical structure, i.e., parts of a text can be identified using their position in this hierarchy. In addition, section titles usually indicate the common topic of their respective sentences. We propose a novel approach to formulate, extract, encode and inject hierarchical structure information explicitly into an extractive summarization model based on a pre-trained, encoder-only Transformer language model (HiStruct+ model), which improves SOTA ROUGEs for extractive summarization on PubMed and arXiv substantially. Using various experimental settings on three datasets (i.e., CNN/DailyMail, PubMed and arXiv), our HiStruct+ model outperforms a strong baseline collectively, which differs from our model only in that the hierarchical structure information is not injected. It is also observed that the more conspicuous hierarchical structure the dataset has, the larger improvements our method gains. The ablation study demonstrates that the hierarchical position information is the main contributor to our model's SOTA performance.
When building NLP models, there is a tendency to aim for broader coverage, often overlooking cultural and (socio)linguistic nuance. In this position paper, we make the case for care and attention to such nuances, particularly in dataset annotation, as well as the inclusion of cultural and linguistic expertise in the process. We present a playbook for responsible dataset creation for polyglossic, multidialectal languages. This work is informed by a study on Arabic annotation of social media content.
In this paper, we study AI approaches to successfully play a 2-4 players, full information, Bomberman variant published on the CodinGame platform. We compare the behavior of three search algorithms: Monte Carlo Tree Search, Rolling Horizon Evolution, and Beam Search. We present various enhancements leading to improve the agents' strength that concern search, opponent prediction, game state evaluation, and game engine encoding. Our top agent variant is based on a Beam Search with low-level bit-based state representation and evaluation function heavy relying on pruning unpromising states based on simulation-based estimation of survival. It reached the top one position among the 2,300 AI agents submitted on the CodinGame arena.
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.
HOLODEC, an airborne cloud particle imager, captures holographic images of a fixed volume of cloud to characterize the types and sizes of cloud particles, such as water droplets and ice crystals. Cloud particle properties include position, diameter, and shape. We present a hologram processing algorithm, HolodecML, that utilizes a neural segmentation model, GPUs, and computational parallelization. HolodecML is trained using synthetically generated holograms based on a model of the instrument, and predicts masks around particles found within reconstructed images. From these masks, the position and size of the detected particles can be characterized in three dimensions. In order to successfully process real holograms, we find we must apply a series of image corrupting transformations and noise to the synthetic images used in training. In this evaluation, HolodecML had comparable position and size estimation performance to the standard processing method, but improved particle detection by nearly 20\% on several thousand manually labeled HOLODEC images. However, the improvement only occurred when image corruption was performed on the simulated images during training, thereby mimicking non-ideal conditions in the actual probe. The trained model also learned to differentiate artifacts and other impurities in the HOLODEC images from the particles, even though no such objects were present in the training data set, while the standard processing method struggled to separate particles from artifacts. The novelty of the training approach, which leveraged noise as a means for parameterizing non-ideal aspects of the HOLODEC detector, could be applied in other domains where the theoretical model is incapable of fully describing the real-world operation of the instrument and accurate truth data required for supervised learning cannot be obtained from real-world observations.
Simultaneous machine translation (SiMT) outputs translation while receiving the streaming source inputs, and hence needs a policy to determine where to start translating. The alignment between target and source words often implies the most informative source word for each target word, and hence provides the unified control over translation quality and latency, but unfortunately the existing SiMT methods do not explicitly model the alignment to perform the control. In this paper, we propose Gaussian Multi-head Attention (GMA) to develop a new SiMT policy by modeling alignment and translation in a unified manner. For SiMT policy, GMA models the aligned source position of each target word, and accordingly waits until its aligned position to start translating. To integrate the learning of alignment into the translation model, a Gaussian distribution centered on predicted aligned position is introduced as an alignment-related prior, which cooperates with translation-related soft attention to determine the final attention. Experiments on En-Vi and De-En tasks show that our method outperforms strong baselines on the trade-off between translation and latency.
Simultaneous machine translation (SiMT) starts translating while receiving the streaming source inputs, and hence the source sentence is always incomplete during translating. Different from the full-sentence MT using the conventional seq-to-seq architecture, SiMT often applies prefix-to-prefix architecture, which forces each target word to only align with a partial source prefix to adapt to the incomplete source in streaming inputs. However, the source words in the front positions are always illusoryly considered more important since they appear in more prefixes, resulting in position bias, which makes the model pay more attention on the front source positions in testing. In this paper, we first analyze the phenomenon of position bias in SiMT, and develop a Length-Aware Framework to reduce the position bias by bridging the structural gap between SiMT and full-sentence MT. Specifically, given the streaming inputs, we first predict the full-sentence length and then fill the future source position with positional encoding, thereby turning the streaming inputs into a pseudo full-sentence. The proposed framework can be integrated into most existing SiMT methods to further improve performance. Experiments on two representative SiMT methods, including the state-of-the-art adaptive policy, show that our method successfully reduces the position bias and thereby achieves better SiMT performance.
Increasingly stringent throughput requirements in the industry necessitate the need for lightweight design of high-precision motion systems to allow for high accelerations, while still achieving accurate positioning of the moving-body. The presence of position dependent dynamics in such motion systems severely limits achievable position tracking performance using conventional sequential loop closing (SLC) control design strategies. This paper presents a novel extension of the conventional SLC design framework towards linear-parameter-varying systems, which allows to circumvent limitations that are introduced by position dependent effects in high-precision motion systems. Advantages of the proposed control design approach are demonstrated in simulation using a high-fidelity model of a moving-magnet planar actuator system, which exhibits position dependency in both actuation and sensing.