Xu Liu

Xu Liu

Auto-generated profile, based on publicly available information

Xu Liu

GRASP Laboratory, University of Pennsylvania, Philadelphia, PA, USA

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 January 2020 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
SCSteven W. Chen
Steven W. Chen
GNGuilherme V. Nardari
Guilherme V. Nardari
ELElijah S. Lee
Elijah S. Lee
CQChao Qu
Chao Qu
XLXu Liu
Xu Liu
VKVijay Kumar
Vijay Kumar
This letter describes an end-to-end pipeline for tree diameter estimation based on semantic segmentation and lidar odometry and mapping. Accurate mapping of this type of environment is challenging since the ground and the trees are surrounded by leaves, thorns and vines, and the sensor typically experiences extreme motion. We propose a semantic feature based pose optimization that simultaneously refines the tree models while estimating the robot pose. The pipeline utilizes a custom virtual reality tool for labeling 3D scans that is used to train a semantic segmentation network. The masked point cloud is used to compute a trellis graph that identifies individual instances and extracts relevant features that are used by the SLAM module. We show that traditional lidar and image based methods fail in the forest environment on both Unmanned Aerial Vehicle (UAV) and hand-carry systems, while our method is more robust, scalable, and automatically generates tree diameter estimations.

24 February 2022 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
XLXu Liu
Xu Liu
GNGuilherme V. Nardari
Guilherme V. Nardari
FCFernando Cladera
Fernando Cladera
YTYuezhan Tao
Yuezhan Tao
AZAlex Zhou
Alex Zhou
VKVijay Kumar
Vijay Kumar
Semantic maps represent the environment using a set of semantically meaningful objects. This representation is storage-efficient, less ambiguous, and more informative, thus facilitating large-scale autonomy and the acquisition of actionable information in highly unstructured, GPS-denied environments. In this letter, we propose an integrated system that can perform large-scale autonomous flights and real-time semantic mapping in challenging under-canopy environments. We detect and model tree trunks and ground planes from LiDAR data, which are associated across scans and used to constrain robot poses as well as tree trunk models. The autonomous navigation module utilizes a multi-level planning and mapping framework and computes dynamically feasible trajectories that lead the UAV to build a semantic map of the user-defined region of interest in a computationally and storage efficient manner. A drift-compensation mechanism is designed to minimize the odometry drift using semantic SLAM outputs in real time, while maintaining planner optimality and controller stability. This leads the UAV to execute its mission accurately and safely at scale.

27 February 2019 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
XLXu Liu
Xu Liu
SCSteven W. Chen
Steven W. Chen
CLChenhao Liu
Chenhao Liu
SSShreyas S. Shivakumar
Shreyas S. Shivakumar
JDJnaneshwar Das
Jnaneshwar Das
VKVijay Kumar
Vijay Kumar
We present a cheap, lightweight, and fast fruit counting pipeline. Our pipeline relies only on a monocular camera, and achieves counting performance comparable to a state-of-the-art fruit counting system that utilizes an expensive sensor suite including a monocular camera, LiDAR and GPS/INS on a mango dataset. Our pipeline begins with a fruit and tree trunk detection component that uses state-of-the-art convolutional neural networks (CNNs). It then tracks fruits and tree trunks across images, with a Kalman Filter fusing measurements from the CNN detectors and an optical flow estimator. Finally, fruit count and map are estimated by an efficient fruit-as-feature semantic structure from motion (SfM) algorithm which converts 2D tracks of fruits and trunks into 3D landmarks, and uses these landmarks to identify double counting scenarios. There are many benefits of developing such a low cost and lightweight fruit counting system, including applicability to agriculture in developing countries, where monetary constraints or unstructured environments necessitate cheaper hardware solutions.

4 February 2022 in IEEE Micro
Verified
Journal Article
Closed access
XLXu Liu
Xu Liu
SCSteven W. Chen
Steven W. Chen
GNGuilherme V. Nardari
Guilherme V. Nardari
CQChao Qu
Chao Qu
FCFernando Cladera
Fernando Cladera
VKVijay Kumar
Vijay Kumar
Mobile robots such as unmanned ground vehicles (UGVs) and unmanned aerial vehicles (UAVs) are increasingly used for precision agriculture. While UGVs have larger payload capabilities and longer operation time, they are limited to 2-D space. This makes UAVs better suited for tasks that require fast coverage, harsh terrain traversal, and high altitude or multilevel operation. However, it remains a challenging task to develop a reliable yet fully autonomous UAV system that can actively extract actionable information in large-scale cluttered agricultural environments. Such a system will have to estimate its own poses, build a map of the environment, navigate through obstacles, and act to gather information with limited onboard computation and battery life. In this survey, we first review recent advances in UAV hardware and software, ranging from novel platforms and sensors to state-of-the-art autonomous navigation, object detection and segmentation, robot localization, and mapping algorithms related to agriculture. We then provide a list of challenges in each field and potential opportunities for the broader adoption of UAVs in precision agriculture.

7 February 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
YTYuezhan Tao
Yuezhan Tao
XLXu Liu
Xu Liu
ISIgor Spasojevic
Igor Spasojevic
SASaurav Agarwal
Saurav Agarwal
VKVijay Kumar
Vijay Kumar
In this letter, we address the problem of exploration and metric-semantic mapping of multi-floor GPS-denied indoor environments using Size Weight and Power (SWaP) constrained aerial robots. Most previous work in exploration assumes that robot localization is solved. However, neglecting the state uncertainty of the agent can ultimately lead to cascading errors both in the resulting map and in the state of the agent itself. Furthermore, actions that reduce localization errors may be at direct odds with the exploration task. We develop a framework that balances the efficiency of exploration with actions that reduce the state uncertainty of the agent. In particular, our algorithmic approach for active metric-semantic SLAM is built upon sparse information abstracted from raw problem data, to make it suitable for SWaP-constrained robots. Furthermore, we integrate this framework within a fully autonomous aerial robotic system that achieves autonomous exploration in cluttered, 3D environments. From extensive real-world experiments, we showed that by including Semantic Loop Closure (SLC), we can reduce the robot pose estimation errors by over 90% in translation and approximately 75% in yaw, and the uncertainties in pose estimates and semantic maps by over 70% and 65%, respectively. Although discussed in the context of indoor multi-floor exploration, our system can be used for various other applications, such as infrastructure inspection and precision agriculture where reliable GPS data may not be available.

6 November 2025 in IEEE Transactions on Robotics
Verified
Journal Article
Closed access
XLXu Liu
Xu Liu
JLJiuzhou Lei
Jiuzhou Lei
APAnkit Prabhu
Ankit Prabhu
YTYuezhan Tao
Yuezhan Tao
ISIgor Spasojevic
Igor Spasojevic
VKVijay Kumar
Vijay Kumar
This paper develops a real-time decentralized metric-semantic SLAM algorithm that enables a heterogeneous robot team to collaboratively construct object-based metric-semantic maps. The proposed framework integrates a data-driven front-end for instance segmentation from either RGBD cameras or LiDARs and a custom back-end for optimizing robot trajectories and object landmarks in the map. To allow multiple robots to merge their information, we design semantics-driven place recognition algorithms that leverage the informativeness and viewpoint invariance of the object-level metric-semantic map for inter-robot loop closure detection. A communication module is designed to track each robot's observations and those of other robots whenever communication links are available. The framework supports real-time, decentralized operation onboard the robots and has been integrated with three types of aerial and ground platforms. We validate its effectiveness through experiments in both indoor and outdoor environments, as well as benchmarks on public datasets and comparisons with existing methods. The framework is open-sourced and suitable for both single-agent and multi-robot real-time metric-semantic SLAM applications.