Papers
9
Total Citations
195
H-Index
6
About
Jiwen Lu is a leading researcher at the intersection of computer vision, robotics, and embodied AI, with a focus on enabling intelligent agents to perceive, reason, and act in complex 3D environments. His work spans 3D scene perception, robotic manipulation, and task planning, where he has made several high-impact contributions. Notably, his 2022 paper on “LiDAR Distillation” (63 citations) addresses the critical beam-induced domain gap in 3D object detection, enabling models trained on high-beam LiDAR data to generalize to lower-beam sensors common in mass-produced robots. In robotic manipulation, his “GE-Grasp” (30 citations) introduces efficient target-oriented grasping in dense clutter, while “Planning Irregular Object Packing” (26 citations) tackles the challenging problem of packing non-regular objects using hierarchical reinforcement learning—both advancing practical warehouse automation. More recently, his work on “ManiGaussian” (33 citations, 2024) leverages dynamic Gaussian splatting for multi-task robotic manipulation, and “Embodied Task Planning with Large Language Models” (18 citations, 2023) bridges commonsense reasoning with robotic execution. With over 200 total citations from these key papers alone, Lu’s research is shaping the next generation of autonomous systems that can perceive, plan, and manipulate the physical world.
Research Focus
Key Achievements
Top Papers
- 1
- 2ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulation33 citations · 2024
- 3GE-Grasp: Efficient Target-Oriented Grasping in Dense Clutter30 citations · 2022
- 4Planning Irregular Object Packing via Hierarchical Reinforcement Learning26 citations · 2022
- 5Embodied Task Planning with Large Language Models18 citations · 2023
- 6
- 7Memory-based Adapters for Online 3D Scene Perception6 citations · 2024
- 8Human Trajectory Prediction via Counterfactual Analysis6 citations · 2021
- 9