Fault-Tolerant Control
Overview
Fault-tolerant control studies how systems can keep operating safely when actuators, sensors, communications, or other components fail or degrade. Common approaches include fault detection and estimation, adaptive control, model-predictive control and control reallocation, alongside learned policies and runtime safety monitors. Methods are tested in settings such as aircraft and spacecraft, drones, legged robots, vehicles, and industrial processes, using both simulations and hardware experiments. A central challenge is handling unfamiliar or simultaneous faults while balancing fast recovery, sustained performance, and guarantees of safety.
Latest papers
31 papers5 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.
Industry is moving toward autonomous, network-connected machines that detect and adapt to changing conditions, including hardware faults. Conventional fault-tolerant design duplicates hardware and reroutes control logic; reinforcement learning (RL) offers a learning-based alternative. This paper presents the first systematic comparison of two RL algorithms -- Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC) -- for integrating fault tolerance into control. Beyond algorithm choice, we investigate four knowledge-transfer strategies: retaining or discarding model parameters, and retaining or discarding storage contents. Performance is evaluated in two Gymnasium environments: Ant-v5 and FetchReachDense-v3. Results show rapid, fault-specific recovery with clear trade-offs. In Ant-v5, retaining PPO's parameters boosts early returns and remains the safest choice across all faults, while retaining SAC's parameters yields mixed outcomes. SAC's early performance further depends on whether the replay buffer is retained: beneficial when prior experiences match current dynamics, but harmful when they diverge. In FetchReachDense-v3, discarding both PPO's and SAC's parameters was most effective under sensor corruption. Across tasks, both algorithms recover near-normal performance within minutes in low-dimensional settings and within days in high-dimensional settings, highlighting a clear trade-off between adaptation speed and asymptotic performance. These findings demonstrate that RL can deliver robust fault tolerance and offer practical guidelines.