We focused on a medical procedure, known as interventional radiology (IR), as the target of robotizing medical surgeries. IR is a general term for treatments that use devices to visualize patients' bodies. Our developed robot, known as Zerobot, specializes in inserting a needle into patients under computer tomography (CT) guidance during surgery. Its surgery is less invasive, and effective in treating small cancer tumors by controlling the temperature of the tip of the inserted needle. Zerobot is originally designed to be remotely controlled by doctors, and has confirmed its surgical ability through first-in-human feasibility trials in 2018. As a current issue, we focus on the supporting function for the operator during the surgery. In an experiment with an animal, Zerobot could not insert the needle into the animal during IR surgery if the needle were bent. Thus, in this study, we aim to make the robot function automatically so that the needle does not bend during surgery. As the first step, we propose a method for estimating the form of the needle using a force sensor. There are three types of needle forms to be classified. The proposed method can distinguish these needle forms by measuring the difference in force sensor data when slightly moving the needle root. In addition, we experimented to confirm the effectiveness of the proposed method.