How to reduce the requirement on training dataset size is a hot topic in deep learning community. One straightforward way is to reuse some pre-trained parameters. Some previous work like Deep transfer learning reuse the model parameters trained for the first task as the starting point for the second task, and semi-supervised learning is trained upon a combination of labeled and unlabeled data. However, the fundamental reason of the success of these methods is unclear. In this paper, the reusability of parameters in each layer of a deep convolutional neural network is experimentally quantified by using a network to do segmentation and auto-encoder task. This paper proves that network parameters can be reused for two reasons: first, the network features are general; Second, there is little difference between the pre-trained parameters and the ideal network parameters. Through the use of parameter replacement and comparison, we demonstrate that reusability is different in BN(Batch Normalization)[7] layer and Convolution layer and some observations: (1)Running mean and running variance plays an important role than Weight and Bias in BN layer.(2)The weight and bias can be reused in BN layers.( 3) The network is very sensitive to the weight of convolutional layer.(4) The bias in Convolution layers are not sensitive, and it can be reused directly.
Convolutional neural network(CNN) has achieved great success in many fields, but due to the huge number of parameters, it is very difficult to study. Then, can we start from the parameters themselves to explore the relationship between the internal parameters of CNN? This paper proposes to use the convolution layer parameters substitution with the same convolution kernel setting to explore the relationship between the internal parameters of CNN and proposes to use the CNN visualization method to check the relationship. Using the visualization method, the forward propagation process of CNN is visualized. It is an intuitive representation of how CNN learns. According to the experiments, this paper believes that 1. Residual layer parameters of ResNet are correlated, and some layers can be substituted for each other; 2. Image segmentation is a process of first learning image texture features and then locating and segmentation.
Artificial Intelligence (AI) has attracted a great deal of attention in recent years. However, alongside all its advancements, problems have also emerged, such as privacy violations, security issues and model fairness. Differential privacy, as a promising mathematical model, has several attractive properties that can help solve these problems, making it quite a valuable tool. For this reason, differential privacy has been broadly applied in AI but to date, no study has documented which differential privacy mechanisms can or have been leveraged to overcome its issues or the properties that make this possible. In this paper, we show that differential privacy can do more than just privacy preservation. It can also be used to improve security, stabilize learning, build fair models, and impose composition in selected areas of AI. With a focus on regular machine learning, distributed machine learning, deep learning, and multi-agent systems, the purpose of this article is to deliver a new view on many possibilities for improving AI performance with differential privacy techniques.
Underwater communication is extremely challenging for small underwater robots that have stringent power and size constraints. In our previous work, we have demonstrated that electrocommunication is an alternative method for small underwater robot communication. This paper presents a new electrocommunication system which utilizes Binary Frequency Shift Keying (2FSK) modulation and deep-learning-based demodulation for underwater robots. We first derive an underwater electrocommunication model which covers both the near-field area and a large transition area outside of the near-field area. The 2FSK modulation is adopted to improve the anti-interference ability of the signal. A deep learning algorithm is used to demodulate the signal by the receiver. Simulations and experiments show that at the same testing condition, the new communication system has a lower bit error rate and a higher data rate than the previous electrocommunication system. The communication system achieves stable communication within the distance of 10 m at a data transfer rate of 5 Kbps with a power consumption of less than 0.1 W. The large improvement of the communication distance in this study further advances the application of electrocommunication
We propose a scalable cooperative control approach which coordinates a group of rigidly connected autonomous surface vessels to track desired trajectories in a planar water environment as a single floating modular structure. Our approach leverages the implicit information of the structure's motion for force and torque allocation without explicit communication among the robots. In our system, a leader robot steers the entire group by adjusting its force and torque according to the structure's deviation from the desired trajectory, while follower robots run distributed consensus-based controllers to match their inputs to amplify the leader's intent using only onboard sensors as feedback. To cope with the complex and highly coupled system dynamics in the water, the leader robot employs a nonlinear model predictive controller (NMPC), where we experimentally estimated the dynamics model of the floating modular structure in order to achieve superior performance for leader-following control. Our method has a wide range of potential applications in transporting humans and goods in many of today's existing waterways. We conducted trajectory and orientation tracking experiments in hardware with three custom-built autonomous modular robotic boats, called Roboat, which are capable of holonomic motions and onboard state estimation. Simulation results with up to 65 robots also prove the scalability of our proposed approach.
This paper presents a novel autonomous surface vessel (ASV), called Roboat II for urban transportation. Roboat II is capable of accurate simultaneous localization and mapping (SLAM), receding horizon tracking control and estimation, and path planning. Roboat II is designed to maximize the internal space for transport and can carry payloads several times of its own weight. Moreover, it is capable of holonomic motions to facilitate transporting, docking, and inter-connectivity between boats. The proposed SLAM system receives sensor data from a 3D LiDAR, an IMU, and a GPS, and utilizes a factor graph to tackle the multi-sensor fusion problem. To cope with the complex dynamics in the water, Roboat II employs an online nonlinear model predictive controller (NMPC), where we experimentally estimated the dynamical model of the vessel in order to achieve superior performance for tracking control. The states of Roboat II are simultaneously estimated using a nonlinear moving horizon estimation (NMHE) algorithm. Experiments demonstrate that Roboat II is able to successfully perform online mapping and localization, plan its path and robustly track the planned trajectory in the confined river, implying that this autonomous vessel holds the promise on potential applications in transporting humans and goods in many of the waterways nowadays.
We propose a novel receding horizon planner for an autonomous surface vehicle (ASV) path planning in urban waterways. The proposed planner is lightweight, as it requires no prior map and is suitable for deployment on platforms with limited computational resources. To find a feasible path in the presence of obstacles, the planner repeatedly generates a graph, which takes the dynamic constraints of the robot into account, using a global reference path. We also propose a novel method for multi-objective motion planning over the graph by leveraging the paradigm of lexicographic optimization and applying it for the first time to graph search within our receding horizon planner. The competing resources of interest are penalized hierarchically during the search. Higher-ranked resources cause a robot to incur non-negative costs over the paths traveled, which are occasionally zero-valued. This is intended to capture problems in which a robot must manage resources such as risk of collision. This leaves freedom for tie-breaking with respect to lower-priority resources; at the bottom of the hierarchy is a strictly positive quantity consumed by the robot, such as distance traveled, energy expended or time elapsed. We conduct experiments in both simulated and real-world environments to validate the proposed planner and demonstrate its capability for enabling ASV navigation in complex environments.
In unsupervised feature learning, sample specificity based methods ignore the inter-class information, which deteriorates the discriminative capability of representation models. Clustering based methods are error-prone to explore the complete class boundary information due to the inevitable class inconsistent samples in each cluster. In this work, we propose a novel clustering based method, which, by iteratively excluding class inconsistent samples during progressive cluster formation, alleviates the impact of noise samples in a simple-yet-effective manner. Our approach, referred to as Progressive Cluster Purification (PCP), implements progressive clustering by gradually reducing the number of clusters during training, while the sizes of clusters continuously expand consistently with the growth of model representation capability. With a well-designed cluster purification mechanism, it further purifies clusters by filtering noise samples which facilitate the subsequent feature learning by utilizing the refined clusters as pseudo-labels. Experiments on commonly used benchmarks demonstrate that the proposed PCP improves baseline method with significant margins. Our code will be available at https://github.com/zhangyifei0115/PCP.
We propose a framework for tightly-coupled lidar inertial odometry via smoothing and mapping, LIO-SAM, that achieves highly accurate, real-time mobile robot trajectory estimation and map-building. LIO-SAM formulates lidar-inertial odometry atop a factor graph, allowing a multitude of relative and absolute measurements, including loop closures, to be incorporated from different sources as factors into the system. The estimated motion from inertial measurement unit (IMU) pre-integration de-skews point clouds and produces an initial guess for lidar odometry optimization. The obtained lidar odometry solution is used to estimate the bias of the IMU. To ensure high performance in real-time, we marginalize old lidar scans for pose optimization, rather than matching lidar scans to a global map. Scan-matching at a local scale instead of a global scale significantly improves the real-time performance of the system, as does the selective introduction of keyframes, and an efficient sliding window approach that registers a new keyframe to a fixed-size set of prior ``sub-keyframes.'' The proposed method is extensively evaluated on datasets gathered from three platforms over various scales and environments.