Search for: All records

While robust optimal control theory provides a rigorous framework to compute robot control policies that are provably safe, it struggles to scale to high- dimensional problems, leading to increased use of deep learning for tractable synthesis of robot safety. Unfortunately, existing neural safety synthesis methods often lack convergence guarantees and solution interpretability. In this paper, we present Minimax Actors Guided by Implicit Critic Stackelberg (MAGICS), a novel adversarial reinforcement learning (RL) algorithm that guarantees local convergence to a minimax equilibrium solution. We then build on this approach to provide local convergence guarantees for a general deep RL-based robot safety synthesis algorithm. Through both simulation studies on OpenAI Gym environ- ments and hardware experiments with a 36-dimensional quadruped robot, we show that MAGICS can yield robust control policies outperforming the state- of-the-art neural safety synthesis methods. 

While the severe underrepresentation of women and non-binary people in open source is widely recognized, there is little empirical data on how the situation has changed over time and which subcommunities have been more effectively reducing the gender imbalance. To obtain a clearer image of gender representation in open source, we compiled and synthesized existing empirical data from the literature, and computed historical trends in the representation of women across 20 open source ecosystems. While inherently limited by the ability of automatic name-based gender inference to capture true gender identities at an individual level, our census still provides valuable population-level insights. Across all and in most ecosystems, we observed a promising upward trend in the percentage of women among code contributors over time, but also high variation in the percentage of women contributors across ecosystems. We also found that, in most ecosystems, women withdraw earlier from open-source participation than men. 

A divide-and-conquer (DAC) machine learning approach was first proposed by Wang et al. to forecast the sea surface height (SSH) of the Loop Current System (LCS) in the Gulf of Mexico. In this DAC approach, the forecast domain was divided into non-overlapping partitions, each of which had their own prediction model. The full domain SSH prediction was recovered by interpolating the SSH across each partition boundaries. Although the original DAC model was able to predict the LCS evolution and eddy shedding more than two months and three months in advance, respectively, growing errors at the partition boundaries negatively affected the model forecasting skills. In the study herein, a new partitioning method, which consists of overlapping partitions is presented. The region of interest is divided into 50%-overlapping partitions. At each prediction step, the SSH value at each point is computed from overlapping partitions, which significantly reduces the occurrence of unrealistic SSH features at partition boundaries. This new approach led to a significant improvement of the overall model performance both in terms of features prediction such as the location of the LC eddy SSH contours but also in terms of event prediction, such as the LC ring separation. We observed an approximate 12% decrease in error over a 10-week prediction, and also show that this method can approximate the location and shedding of eddy Cameron better than the original DAC method.