In Human-Robot Collaboration scenarios, safety must be ensured by a risk management process that requires the execution of computationally-expensive perception models (e.g., based on computer vision) in real-time. However, robots usually have constrained hardware resources which hinder achieving responses in a timely manner, resulting in unsafe operations. Although Multi- access Edge Computing allows robots to offload complex tasks to servers on the edge in order to meet real-time requirements, this might not be always possible due to dynamic changes in the network that can cause congestion or failures. This work proposes a safety-based task offloading strategy to address this problem. The goal is to intelligently use edge resources to reduce delays in the risk management process and consequently enhance safety.