The Atkins team presents a highly automated Sort & Segregate system using a robotic arm mounted on a modular system that can be deployed to identify, sort and segregate radioactive waste for safe recycling or disposal. The robot will confront an unorganised mass of radioactive waste comprising a diverse range of objects. To process this waste, the robot will first identify an individual waste item using its vision system. At first the robot may recognise some waste but will require training by an operative to identify new waste types by sight. The more its vision system is used, the more autonomous the process becomes through machine learning. The system will also measure each item's weight, volume, surface area and composition for efficient sorting and packing. Once identified, waste is then radiologically and chemically characterised and sorted. Each item is picked up by the robotic arm, its level of radioactivity is monitored, and it is chemically analysed. The information on the item's physical characteristics, material type and radioactivity level is used to sort the item into the correct waste stream for safe recycling or storage, aided by efficient packing ensured by the vision system's algorithms. Records will be kept for each waste item and for each waste container produced. These records maintain traceability of the hazardous waste. This project innovates on current state-of-the-art by removing the person from the process. This means that there is less risk to operators from working in hazardous environments, and less risk of human error in such a repetitive task. The process will be safer, quicker and cheaper than a manual system, offering savings to the UK taxpayer on the cost of decommissioning redundant nuclear equipment and facilities. Combining a robotic arm with machine learning, vision systems, and nuclear and chemical characterisation will mark a new advancement in nuclear decommissioning. The robot arm can be of any model and size to suit the waste type. The intelligent vision system is a key innovation, as it automates the recognition of different forms of waste through machine learning. Operator involvement is minimised, creating an efficient, low-waste workflow that can adapt to location, segregate waste by various measurable criteria, and will improve the more it is deployed. Waste generated by nuclear decommissioning is therefore dealt with safely, quickly and cheaply, with minimal human interaction, efficiently packing waste containers, and with a diligent recycling process.