Papers
3
Total Citations
72
H-Index
3
About
Abel Cherouat’s research bridges the critical gap between robotic manipulation and advanced computer vision, with a primary focus on enabling autonomous systems to grasp objects reliably in complex, cluttered environments. His most cited work, "Grasping With Occlusion-Aware Ally Method in Complex Scenes" (2024), has already garnered 64 citations, demonstrating its immediate impact on the field. In this study, Cherouat introduces a novel vision-driven approach that enhances robotic arm target grasping by intelligently handling occlusions, allowing robots to identify, localize, and retrieve objects even when partially hidden—a persistent challenge in real-world automation. Beyond robotics, Cherouat has also contributed to manufacturing engineering, notably investigating springback effects during single point incremental forming (2018), where he optimized tool paths to improve precision in sheet metal prototyping. His 2023 work on "Detection-driven 3D masking for efficient object grasping" further refines 3D scene understanding for robotic manipulation. Cherouat’s research is characterized by its practical orientation: he develops algorithms that directly improve the reliability and efficiency of automated systems, from factory floors to assistive robotics. His growing citation record underscores his role in advancing occlusion-aware perception, a cornerstone for next-generation autonomous grasping.
Research Focus
Key Achievements
Top Papers
- 1Grasping With Occlusion-Aware Ally Method in Complex Scenes64 citations · 2024
- 2
- 3Detection-driven 3D masking for efficient object grasping3 citations · 2023