Etor Arza, Luca Girardi, Gabriel Maquignaz, Javier Paez, Stefan Leutenegger, Stefano Mintchev, Kostas Alexis
原文摘要
Aerial robots operating in cluttered environments may encounter openings narrower than their nominal width. Existing passively morphing drones reduce their width upon traversal, but they typically involve human-made designs, which can struggle to find the right balance among folding ratio, flight efficiency, and control tracking performance. We introduce a closed-loop design method that jointly optimizes quadrotor geometry and the torque-deflection response of two passively folding arms driven by the success rate in simulation for contact-mediated gap traversal. An optimization algorithm samples candidate designs that are evaluated in a contact-based simulation of the traversal task, where the task success rate is used as a feedback signal to sample progressively better designs over time. The resulting prototype passively reduces its width from 31.3 to 14.1 cm and traverses a 15 cm wide opening at a 2 m/s reference speed. It also tolerates gap approach-angle errors of up to 30 degrees and folds through a 40 cm long confined passage. Compared to a rigid twin, the soft configuration adds only 2 mm of position RMSE and less than 1% electrical power during contact-free flight. These results show that task-driven closed-loop design optimization can produce passively morphing airframes that are compact under contact, tolerant to approach error, and effectively rigid during nominal flight.
Reinforcement learning commonly exhibits non-monotonic performance dynamics in single-task settings. During learning, a sequence of policies is generated whose true performance is unknown and may oscillate significantly across iterations. Despite this well-known phenomenon, standard experimental practice typically reports either the final visited policy or the best among periodically evaluated ones, implicitly assuming that these selection criteria reliably approximate the best-performing policy visited throughout the entire sequence. In this work, we present an empirical study on the implications of non-monotonicity for policy selection in single-task policy-based reinforcement learning. We introduce post-hoc diagnostic metrics to characterize performance degradation and assess the accuracy and efficiency of different selection criteria. These metrics allow us to evaluate commonly used selection strategies across standard continuous-control benchmarks using a well-established on-policy actor-critic method. Our results show that, in this representative experimental setting, widely adopted selection practices can deviate considerably from the best policy encountered during learning, leading to underperforming estimates and suboptimal use of computational resources. As an alternative, we recommend a validation-based policy selection strategy constrained by computational cost, which provides a more consistent and accurate approximation of the best visited policy while improving selection efficiency. Overall, our findings highlight policy selection as an underexplored factor in the evaluation protocols of reinforcement learning and motivate further study on explicit and standardized validation-based selection procedures.