Runjian Chen

Bio: Runjian Chen is an academic researcher from Zhejiang University. The author has contributed to research in topics: Monte Carlo localization & Point cloud. The author has an hindex of 1, co-authored 5 publications receiving 7 citations.

RaLL: End-to-End Radar Localization on Lidar Map Using Differentiable Measurement Model

Abstract: Compared to the onboard camera and laser scanner, radar sensor provides lighting and weather invariant sensing, which is naturally suitable for long-term localization under adverse conditions. However, radar data is sparse and noisy, resulting in challenges for radar mapping. On the other hand, the most popular available map currently is built by lidar. In this paper, we propose an end-to-end deep learning framework for Radar Localization on Lidar Map (RaLL) to bridge the gap, which not only achieves the robust radar localization but also exploits the mature lidar mapping technique, thus reducing the cost of radar mapping. We first embed both sensor modals into a common feature space by a neural network. Then multiple offsets are added to the map modal for exhaustive similarity evaluation against the current radar modal, yielding the regression of the current pose. Finally, we apply this differentiable measurement model to a Kalman Filter (KF) to learn the whole sequential localization process in an end-to-end manner. The whole learning system is differentiable with the network based measurement model at the front-end and KF at the back-end. To validate the feasibility and effectiveness, we employ multi-session multi-scene datasets collected from the real world, and the results demonstrate that our proposed system achieves superior performance over 90km driving, even in generalization scenarios where the model training is in UK, while testing in South Korea. We also release the source code publicly.

Deep Samplable Observation Model for Global Localization and Kidnapping.

Abstract: Global localization and kidnapping are two challenging problems in robot localization. The popular method, Monte Carlo Localization (MCL) addresses the problem by iteratively updating a set of particles with a "sampling-weighting" loop. Sampling is decisive to the performance of MCL [1]. However, traditional MCL can only sample from a uniform distribution over the state space. Although variants of MCL propose different sampling models, they fail to provide an accurate distribution or generalize across scenes. To better deal with these problems, we present a distribution proposal model, named Deep Samplable Observation Model (DSOM). DSOM takes a map and a 2D laser scan as inputs and outputs a conditional multimodal probability distribution of the pose, making the samples more focusing on the regions with higher likelihood. With such samples, the convergence is expected to be more effective and efficient. Considering that the learning-based sampling model may fail to capture the true pose sometimes, we furthermore propose the Adaptive Mixture MCL (AdaM MCL), which deploys a trusty mechanism to adaptively select updating mode for each particle to tolerate this situation. Equipped with DSOM, AdaM MCL can achieve more accurate estimation, faster convergence and better scalability compared to previous methods in both synthetic and real scenes. Even in real environments with long-term changing, AdaM MCL is able to localize the robot using DSOM trained only by simulation observations from a SLAM map or a blueprint map.

Deep Samplable Observation Model for Global Localization and Kidnapping

Abstract: Global localization and kidnapping are two challenging problems in robot localization. The popular method, Monte Carlo Localization (MCL) addresses the problem by iteratively updating a set of particles with a “sampling-weighting” loop. Sampling is decisive to the performance of MCL [1] . However, traditional MCL can only sample from a uniform distribution over the state space. Although variants of MCL propose different sampling models, they fail to provide an accurate distribution or generalize across scenes. To better deal with these problems, we present a distribution proposal model named Deep Samplable Observation Model (DSOM). DSOM takes a map and a 2D laser scan as inputs and outputs a conditional multimodal probability distribution of the pose, making the samples more focusing on the regions with higher likelihood. With such samples, the convergence is expected to be more effective and efficient. Considering that the learning-based sampling model may fail to capture the accurate pose sometimes, we furthermore propose the Adaptive Mixture MCL (AdaM MCL), which deploys a trusty mechanism to adaptively select updating mode for each particle to tolerate this situation. Equipped with DSOM, AdaM MCL can achieve more accurate estimation, faster convergence and better scalability than previous methods in both synthetic and real scenes. Even in real environments with long-term changes, AdaM MCL is able to localize the robot using DSOM trained only by simulation observations from a SLAM map or a blueprint map. Source code for this paper is available here: https://github.com/Runjian-Chen/AdaM_MCL .

From Virtuality To Reality: A Learning-based Point Cloud Labeling Method With Synthesis Scene

Abstract: This paper proposes a machine learning based point cloud labeling algorithm. To classify point cloud in a sparse scan of both virtual and real scene as basic geometrical elements like planar and edge, a rendering dataset in virtual environment is created and labeled. Then the principal component analysis (PCA) is applied to calculate local geometrical features of point cloud. An in-depth analysis is performed by training several machine learning models with PCA features and experiments in which the trained models are applied to on both rendering point cloud and laser scan of real scene are conducted to validate that our approach is scale-invariant and effective on both rendering point cloud and point cloud of real scene.

A Samplable Multimodal Observation Model for Global Localization and Kidnapping.

Abstract: Global localization and kidnapping are two challenging problems in robot localization. The popular method, Monte Carlo Localization (MCL) addresses the problem by sampling uniformly over the state space, which is unfortunately inefficient when the environment is large. To better deal with the the problems, we present a proposal model, named Deep Multimodal Observation Model (DMOM). DMOM takes a map and a 2D laser scan as inputs and outputs a conditional multimodal probability distribution of the pose, making the samples more focusing on the regions with higher likelihood. With such samples, the convergence is expected to be much efficient. Considering that learning based Samplable Observation Model may fail to capture the true pose sometimes, we furthermore propose the Adaptive Mixture MCL, which adaptively selects updating mode for each particle to tolerate this situation. Equipped with DMOM, Adaptive Mixture MCL can achieve more accurate estimation, faster convergence and better scalability compared with previous methods in both synthetic and real scenes. Even in real environment with long-term changing, Adaptive Mixture MCL is able to localize the robot using DMON trained only on simulated observations from a SLAM map, or even a blueprint map.

I and i

Abstract: There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality. Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

Are We Ready for Radar to Replace Lidar in All-Weather Mapping and Localization?

Abstract: We present an extensive comparison between three topometric localization systems: radar-only, lidar-only, and a cross-modal radar-to-lidar system across varying seasonal and weather conditions using the Boreas dataset. Contrary to our expectations, our experiments showed that our lidar-only pipeline achieved the best localization accuracy even during a snowstorm. Our results seem to suggest that the sensitivity of lidar localization to moderate precipitation has been exaggerated in prior works. However, our radar-only pipeline was able to achieve competitive accuracy with a much smaller map. Furthermore, radar localization and radar sensors still have room to improve and may yet prove valuable in extreme weather or as a redundant backup system.

Millimeter Wave FMCW RADARs for Perception, Recognition and Localization in Automotive Applications: A Survey

Abstract: MmWave (millimeter wave) Frequency Modulated Continuous Waves (FMCW) RADARs are sensors based on frequency-modulated electromagnetic which see their environment in 3D at a long-range. The recent introduction of millimeter-wave RADARs with frequencies from 60 GHz to 300 GHz has broadened their potential applications thanks to their improved accuracy in angle, range, and velocity. MmWave FMCW RADARs have better resolution and accuracy than narrowband and ultra-wideband (UWB) RADARs. In comparison with cameras and LiDARs, they possess several strong advantages such as long-range perception, robustness to lightning, and weather conditions while being cheaper. However, their noisy and lower-density outputs even compared to other technologies of RADARs, and their ability to measure the targets’ velocities require specific algorithms tailored for them. Working principles of mmWave FMCW RADARs are presented as well as the separate ways to represent data and their applications. This paper describes algorithms and applications adapted or developed for these sensors in automotive applications. Finally, current challenges and directions for future works are presented.

An Improved Localization of Mobile Robotic System Based on AMCL Algorithm

Abstract: In the Mobile Robotics domain, the ability of robots to locate themselves is one of the most important events. By locating, mobile robots can obtain information about the environment and continuously track their position and direction. Among localization algorithms, the Adaptive Monte Carlo Localization (AMCL) algorithm is applied most often in robot localization, a two-dimensional environment probabilistic localization system to improve the problems such as high computational complexity and hijacking of mobile robots that exist in the traditional MCL method. The proposed method is based on 2D laser information, range finder information, and AMCL to accomplish the localization task. Furthermore, an optimized AMCL algorithm is proposed to increase the accuracy of localization in terrain that is easy to fail to locate, have a chance to locate successfully when a localization error occurs, and apply the optimized AMCL to the mobile robot system. From the experimental results, we know that the improved AMCL algorithm can enhance the positioning accuracy of the robot effectively, which has better practicality than the original AMCL.