Autonomous vehicles (AVs) technology is expected to provide many benefits for the society such as providing safe transportation to the community and reducing the number of accidents on the roads. With the emergence of AVs, the conventional safety infrastructure in which humans drive their vehicles will need to be upgraded in order to take full advantage of the new technology. AVs are responsible for the different aspects of driving, namely: perception, decision making and taking action. Capturing data and diagnosing issues becomes imperative in this new transportation system because an error might be an indication of a systemic problem which may lead to future accidents or failures. Therefore, any AV accident must be dealt with seriously. Unfortunately, current procedures and the type of data collected during the investigation of an accident is not sufficient; For example, AV minor accidents are not investigated in depth as it is with AV major accidents and therefore, if the cause of the accident is a systemic issue, then it might cause more accidents in the future. The main goal of this paper is to explore the requirements for accident reports for incidents involving AVs and the procedures to escalate issues to avoid systemic risks. All the information available about AV accidents, regardless of the severity of the accident, will be analyzed and studied. This paper will present three recommendations; An updated law enforcement accident report, an escalation procedure that depends on the diagnosis of the fault and a database of AV accidents to enable ongoing learning to find systemic issues.