Development of computational techniques, robotics, 3D printing and materials technologies enables the creation of advanced robotic systems that can autonomously reproduce and evolve. Emerging robotic evolution technology challenges existing AI ethics. The inherent adaptability, stochasticity and complexity of evolutionary systems pose numerous threats. It is difficult to underestimate the possible implications of two key functionalities of evolving robots: self-replication and random change of robot form and behavior. Self-replication allows robots to reproduce without human intervention. Mutations or random evolutionary changes can lead to undesirable and harmful behavior of robots, threatening human interests. Whenever a technology is developed that is not under direct human control and the process is unpredictable, questions of risk and liability arise. The article addresses both possible risk of harm and liability in connection with the key issue of human control over the process of evolution. The issue of responsibility for artificial intelligence was considered to be particularly important from both an ethical and legal point of view. In general, responsibility covers the full spectrum of events ex post (who is at fault, what was the reason), and ex ante (what actions should be taken to reduce the risk, i.e. what is negligence and who commits it), and usually rests with people. The problem, however, is the existence of gaps in the scope of liability for damages or adverse events involving people and artificial intelligence systems that cannot be filled with traditional concepts of assigning responsibility. The article indicates a method of comprehensively solving the problem of gaps in liability for artificial intelligence, proposed in the literature, based on the idea of designing social engineering systems that enable “meaningful human control”, i.e. systems adapted to human intentions and capabilities. The aim of the article is to indicate the urgent need for a continuous search for an answer to the question of how to responsibly control the evolution of robots.