Robots are becoming increasingly integrated into our lives, assisting us invarious tasks. To ensure effective collaboration between humans and robots, itis essential that they understand our intentions and anticipate our actions. Inthis paper, we propose a Human-Object Interaction (HOI) anticipation frameworkfor collaborative robots. We propose an efficient and robust transformer-basedmodel to detect and anticipate HOIs from videos. This enhanced anticipationempowers robots to proactively assist humans, resulting in more efficient andintuitive collaborations. Our model outperforms state-of-the-art results in HOIdetection and anticipation in VidHOI dataset with an increase of 1.76% and1.04% in mAP respectively while being 15.4 times faster. We showcase theeffectiveness of our approach through experimental results in a real robot,demonstrating that the robot's ability to anticipate HOIs is key for betterHuman-Robot Interaction. More information can be found on our project webpage:https://evm7.github.io/HOI4ABOT_page/