Author name cluster

Jun Lv

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.

7 papers

2 author rows

EAAI Journal 2026 Journal Article

Adaptive learning guided dual-function scheduling for delay-bounded quality of service in energy-constrained fifth-generation network slices

Jun Lv
Peigang Wei
Xiaofeng Nong
Xiaobo Liang

The rapid growth of latency-sensitive applications such as live video streaming, telemedicine, and emergency communications in fifth-generation mobile networks has intensified the need for time-bounded Quality of Service guarantees while maintaining energy efficiency. Within the context of network slicing, heterogeneous traffic patterns, rapid variations in user density, and stringent energy constraints pose major challenges to conventional scheduling approaches, which typically rely on fixed priority rules or non-adaptive parameters and therefore suffer from degraded performance under high network load. This paper proposes an Adaptive Learning Guided Dual-Function Scheduling framework to deliver delay-bounded Quality of Service in energy-constrained fifth-generation network slices. The proposed scheduler integrates a bi-functional prioritization mechanism, combining exponential and logarithmic components, with a lightweight Artificial Intelligence–based online learning agent. This learning agent adaptively tunes scheduling parameters based on real-time observations of energy consumption trends, traffic intensity, queue dynamics, and delay stability, enabling context-aware and energy-efficient resource allocation. From a computational perspective, the proposed approach is designed to maintain low processing overhead, making it suitable for deployment in radio access network nodes with limited computational capabilities. Extensive system-level simulations conducted on a fifth-generation network slicing platform demonstrate that the proposed method significantly reduces average latency, lowers packet loss, and decreases overall energy consumption, while preserving a high level of fairness among network slices. Compared with existing benchmark scheduling schemes, the proposed Artificial Intelligence–enabled framework consistently achieves superior performance under both moderate and heavy traffic conditions.

Details DOI

IROS Conference 2025 Conference Paper

DiffGen: Robot Demonstration Generation via Differentiable Physics Simulation, Differentiable Rendering, and Vision-Language Model

Yang Jin
Jun Lv
Shuqiang Jiang
Cewu Lu

Generating robot demonstrations through simulation is widely recognized as an effective way to scale up robot data. Previous work often trained reinforcement learning agents to generate expert policies, but this approach lacks sample efficiency. Recently, a line of work has attempted to generate robot demonstrations via differentiable simulation, which is promising but heavily relies on reward design, a labor-intensive process. In this paper, we propose DiffGen, a novel framework that integrates differentiable physics simulation, differentiable rendering, and a vision-language model to enable automatic and efficient generation of robot demonstrations. Given a simulated robot manipulation scenario and a natural language instruction, DiffGen can generate realistic robot demonstrations by minimizing the distance between the embedding of the language instruction and the embedding of the simulated observation after manipulation in representation space. The embeddings are obtained from the vision-language model, and the optimization is achieved by calculating and descending gradients through the differentiable simulation, differentiable rendering, and vision-language model components. Experiments demonstrate that with DiffGen, we could efficiently and effectively generate robot data with minimal human effort or training time. The videos of the results can be accessed at https://sites.google.com/view/diffgen.

Details

ICRA Conference 2025 Conference Paper

Human-Agent Joint Learning for Efficient Robot Manipulation Skill Acquisition

Shengcheng Luo
Quanquan Peng
Jun Lv
Kaiwen Hong
Katherine Driggs-Campbell
Cewu Lu
Yonglu Li 0001

Employing a teleoperation system for gathering demonstrations offers the potential for more efficient learning of robot manipulation. However, teleoperating a robot arm equipped with a dexterous hand or gripper, via a teleoperation system presents inherent challenges due to the task's high dimensionality, complexity of motion, and differences between physiological structures. In this study, we introduce a novel system for joint learning between human operators and robots, that enables human operators to share control of a robot end-effector with a learned assistive agent, simplifies the data collection process, and facilitates simultaneous human demonstration collection and robot manipulation training. As data accumulates, the assistive agent gradually learns. Consequently, less human effort and attention are required, enhancing the efficiency of the data collection process. It also allows the human operator to adjust the control ratio to achieve a tradeoff between manual and automated control. We conducted experiments in both simulated environments and physical realworld settings. Through user studies and quantitative evaluations, it is evident that the proposed system could enhance data collection efficiency and reduce the need for human adaptation while ensuring the collected data is of sufficient quality for downstream tasks. For more details, please refer to our webpage https://norweig1an.github.io/HAJL.github.io/.

Details

IROS Conference 2025 Conference Paper

Knowledge-Driven Imitation Learning: Enabling Generalization Across Diverse Conditions

Zhuochen Miao
Jun Lv
Hongjie Fang
Yang Jin
Cewu Lu

Imitation learning has emerged as a powerful paradigm in robot manipulation, yet its generalization capability remains constrained by object-specific dependencies in limited expert demonstrations. To address this challenge, we propose knowledge-driven imitation learning, a framework that leverages external structural semantic knowledge to abstract object representations within the same category. We introduce a novel semantic keypoint graph as a knowledge template and develop a coarse-to-fine template-matching algorithm that optimizes both structural consistency and semantic similarity. Evaluated on three real-world robotic manipulation tasks, our method achieves superior performance, surpassing image-based diffusion policies with only one-quarter of the expert demonstrations. Extensive experiments further demonstrate its robustness across novel objects, backgrounds, and lighting conditions. This work pioneers a knowledge-driven approach to data-efficient robotic learning in real-world settings. Code and more materials are available on knowledge-driven.github.io.

Details

IROS Conference 2025 Conference Paper

SIME: Enhancing Policy Self-Improvement with Modal-level Exploration

Yang Jin
Jun Lv
Wenye Yu
Hongjie Fang
Yonglu Li 0001
Cewu Lu

Self-improvement requires robotic systems to initially learn from human-provided data and then gradually enhance their capabilities through interaction with the environment. This is similar to how humans improve their skills through continuous practice. However, achieving effective self-improvement is challenging, primarily because robots tend to repeat their existing abilities during interactions, often failing to generate new, valuable data for learning. In this paper, we identify the key to successful self-improvement: modal-level exploration and data selection. By incorporating a modal-level exploration mechanism during policy execution, the robot can produce more diverse and multi-modal interactions. At the same time, we select the most valuable trials and high-quality segments from these interactions for learning. We successfully demonstrate effective robot self-improvement on both simulation benchmarks and real-world experiments. The capability for self-improvement will enable us to develop more robust and high-success-rate robotic control strategies at a lower cost. Our code and experiment scripts are available at ericjin2002.github.io/SIME.

Details

ICRA Conference 2022 Conference Paper

SAGCI-System: Towards Sample-Efficient, Generalizable, Compositional, and Incremental Robot Learning

Jun Lv
Qiaojun Yu
Lin Shao 0002
Wenhai Liu
Wenqiang Xu
Cewu Lu

Building general-purpose robots to perform a diverse range of tasks in a large variety of environments in the physical world at the human level is extremely challenging. According to [1], it requires the robot learning to be sample-efficient, generalizable, compositional, and incremental. In this work, we introduce a systematic learning framework called SAGCI-system towards achieving these above four requirements. Our system first takes the raw point clouds gathered by the camera mounted on the robot's wrist as the inputs and produces initial modeling of the surrounding environment represented as a file of Unified Robot Description Format (URDF). Our system adopts a learning-augmented differentiable simulation that loads the URDF. The robot then utilizes the interactive perception to interact with the environment to online verify and modify the URDF. Leveraging the differentiable simulation, we propose a model-based learning algorithm combining object-centric and robot-centric stages to efficiently produce policies to accomplish manipulation tasks. We apply our system to perform articulated object manipulation tasks, both in the simulation and the real world. Extensive experiments demonstrate the effectiveness of our proposed learning framework. Supplemental materials and videos are available on our project webpage https://sites.google.com/view/egci.

Details

ICRA Conference 2020 Conference Paper

6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints

Chen Wang 0053
Roberto Martín-Martín
Danfei Xu
Jun Lv
Cewu Lu
Li Fei-Fei 0001
Silvio Savarese
Yuke Zhu

We present 6-PACK, a deep learning approach to category-level 6D object pose tracking on RGB-D data. Our method tracks in real time novel object instances of known object categories such as bowls, laptops, and mugs. 6-PACK learns to compactly represent an object by a handful of 3D keypoints, based on which the interframe motion of an object instance can be estimated through keypoint matching. These keypoints are learned end-to-end without manual supervision in order to be most effective for tracking. Our experiments show that our method substantially outperforms existing methods on the NOCS category-level 6D pose estimation benchmark and supports a physical robot to perform simple vision-based closed-loop manipulation tasks. Our code and video are available at https://sites.google.com/view/6packtracking.

Details