Dennis Hoftijzer

University of Twente

Papers

1

Total Citations

2

H-Index

1

About

Dennis Hoftijzer is a researcher at the forefront of embodied AI and deep reinforcement learning, with a primary focus on advancing robotic navigation and perception. His most cited work, "Language-Based Augmentation to Address Shortcut Learning in Object-Goal Navigation" (2023), tackles a critical challenge in robotics: the tendency of deep reinforcement learning agents to rely on environmental shortcuts rather than robust visual cues when locating objects like a fridge in simulated homes. By introducing language-based data augmentation, Hoftijzer’s approach enhances the generalization and reliability of Object-Goal Navigation (ObjectNav) systems, reducing overfitting to simulator-specific biases. This contribution is vital for bridging the gap between simulation and real-world deployment, where robots must adapt to unpredictable environments. Though his citation count of 2 reflects the recency of his work, its impact is growing within the embodied AI community, where shortcut learning remains a pressing issue. Hoftijzer’s research underscores a commitment to building more intelligent, adaptable robots, making him a promising voice in the field of autonomous navigation and human-robot interaction.

Research Focus

Key Achievements

1
H-Index
1
Papers
2
Total Citations
2
Avg Citations/Paper
🏆 Most Cited Paper
Language-Based Augmentation to Address Shortcut Learning in Object-Goal Navigation
2 citations · 2023
📈 Most Prolific Year: 2023 (1 Papers)
🤝 Key Collaborators: 2
🏛 Institutions: University of Twente

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago