Author name cluster

Chen Fu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

TCS Journal 2023 Journal Article

Model checking differentially private properties

Depeng Liu
Bow-Yaw Wang
Chen Fu
Lijun Zhang

With the explosion of digital data collected from social apps, privacy protection regulations have been issued by almost all countries. Differential privacy is proposed as a successful technique to make use of these data, without leaking personal private data at the same time. In this paper, we investigate logical reasoning for differential privacy properties and propose model checking algorithms. We introduce the branching time temporal logic dpCTL* to specify differentially private properties. Several mechanisms in differential privacy are formalized as Markov chains or Markov decision processes. In our framework, we show that subtle privacy conditions are specified by dpCTL*. In order to verify privacy properties automatically, model checking problems are investigated. We develop a model checking algorithm for Markov chains. Model checking dpCTL* properties on Markov decision processes however is shown to be undecidable. Therefore, we propose a sound algorithm to verify these properties in Markov decision processes. We implement our model checking algorithm into a tool, based on the PRISM language, as well as show the experimental results and a case study of stream processing in differential privacy under the essential fairness assumptions.

Details DOI

ICRA Conference 2021 Conference Paper

ENCODE: a dEep poiNt Cloud ODometry nEtwork

Yihuan Zhang
Liang Wang
Chen Fu
Yifan Dai
John M. Dolan

Ego-motion estimation is a key requirement for the simultaneous localization and mapping (SLAM) problem. The traditional pipeline goes through feature extraction, feature matching and pose estimation, whose performance depends on the manually designed features. In this paper, we are motivated by the strong performance of deep learning methods in other computer vision and robotics tasks. We replace hand-crafted features with a neural network and directly estimate the relative pose between two adjacent scans from a LiDAR sensor using ENCODE: a dEep poiNt Cloud ODometry nEtwork. Firstly, a spherical projection of the input point cloud is performed to acquire a multi-channel vertex map. Then a multi-layer network backbone is applied to learn the abstracted features and a fully connected layer is adopted to estimate the 6-DoF ego-motion. Additionally, a map-to-map optimization module is applied to update the local poses and output a smooth map. Experiments on multiple datasets demonstrate that the proposed method achieves the best performance in comparison to state-of-the-art methods and is capable of providing accurate poses with low drift in various kinds of scenarios.

Details

ICRA Conference 2021 Conference Paper

Linear Inverse Problem for Depth Completion with RGB Image and Sparse LIDAR Fusion

Chen Fu
Christoph Mertz
John M. Dolan

Comprehensive depth information from surrounding scenes is important for perception in autonomous driving and robots. Sparse LIDAR sensors give a low-density point cloud of the environment, but are more affordable than their high-density counterparts. In this paper, we propose a novel sensor fusion architecture for sparse LIDAR depth completion. Instead of the traditional end-to-end neural network-based algorithm, we formulate depth completion as a Linear Inverse Problem (LIP) with a multi-modal proximal operator. This sensor fusion architecture allows a better signal prior and finds the unique optimal solution to the LIP. Instead of learning a unified network for the sparse input which treats pixels evenly, the proposed architecture guarantees both the data consistency and smoothness of the predicted depth map. To demonstrate the performance of our algorithm, we benchmark on the simulation dataset TartanAir, and the real indoor NYUdepthv2 and real outdoor KITTI datasets. Our proposed method outperforms previous methods and uses fewer parameters in both indoor and outdoor datasets.

Details

IROS Conference 2020 Conference Paper

Depth Completion via Inductive Fusion of Planar LIDAR and Monocular Camera

Chen Fu
Chiyu Dong
Christoph Mertz
John M. Dolan

Modern high-definition LIDAR is expensive for commercial autonomous driving vehicles and small indoor robots. An affordable solution to this problem is fusion of planar LIDAR with RGB images to provide a similar level of perception capability. Even though state-of-the-art methods provide approaches to predict depth information from limited sensor input, they are usually a simple concatenation of sparse LIDAR features and dense RGB features through an end-to-end fusion architecture. In this paper, we introduce an inductive late-fusion block which better fuses different sensor modalities inspired by a probability model. The proposed demonstration and aggregation network propagates the mixed context and depth features to the prediction network and serves as a prior knowledge of the depth completion. This late-fusion block uses the dense context features to guide the depth prediction based on demonstrations by sparse depth features. In addition to evaluating the proposed method on benchmark depth completion datasets including NYUDepthV2 and KITTI, we also test the proposed method on a simulated planar LIDAR dataset. Our method shows promising results compared to previous approaches on both the benchmark datasets and simulated dataset with various 3D densities.

Details

IJCAI Conference 2018 Conference Paper

Model Checking Probabilistic Epistemic Logic for Probabilistic Multiagent Systems

Chen Fu
Andrea Turrini
Xiaowei Huang
Lei Song
Yuan Feng
Lijun Zhang

In this work we study the model checking problem for probabilistic multiagent systems with respect to the probabilistic epistemic logic PETL, which can specify both temporal and epistemic properties. We show that under the realistic assumption of uniform schedulers, i. e. , the choice of every agent depends only on its observation history, PETL model checking is undecidable. By restricting the class of schedulers to be memoryless schedulers, we show that the problem becomes decidable. More importantly, we design a novel algorithm which reduces the model checking problem into a mixed integer non-linear programming problem, which can then be solved by using an SMT solver. The algorithm has been implemented in an existing model checker and experiments are conducted on examples from the IPPC competitions.

PDF Details