Aiming to develop a more robust and intelligent heterogeneous system for adversarial catching in security and rescue tasks, in this article, we discuss the specialities of applying asymmetric self-play and curriculum learning techniques to deal with the increasing heterogeneity and number of different robots in modern heterogeneous multirobot systems (HMRS). Our method, based on actor-critic multiagent reinforcement learning, provides a framework that can enable cooperative behaviors among heterogeneous multirobot teams. This leads to the development of an HMRS for complex catching scenarios that involve several robot teams and real-world constraints. We conduct simulated experiments to evaluate different mechanisms' influence on our method's performance, and real-world experiments to assess our system's performance in complex real-world catching problems. In addition, a bridging study is conducted to compare our method with a state-of-the-art method called S2M2 in heterogeneous catching problems, and our method performs better in adversarial settings. As a result, we show that the proposed framework, through fusing asymmetric self-play and curriculum learning during training, is able to successfully complete the HMRS catching task under realistic constraints in both simulation and the real world, thus providing a direction for future large-scale intelligent security & rescue HMRS.

Reinforcement learning methods can achieve significant performance but require a large amount of training data collected on the same robotic platform. A policy trained with expensive data is rendered useless after making even a minor change to the robot hardware. In this paper, we address the challenging problem of adapting a policy, trained to perform a task, to a novel robotic hardware platform given only few demonstrations of robot motion trajectories on the target robot. We formulate it as a few-shot meta-learning problem where the goal is to find a meta-model that captures the common structure shared across different robotic platforms such that data-efficient adaptation can be performed. We achieve such adaptation by introducing a learning framework consisting of a probabilistic gradient-based meta-learning algorithm that models the uncertainty arising from the few-shot setting with a low-dimensional latent variable. We experimentally evaluate our framework on a simulated reaching and a real-robot picking task using 400 simulated robots generated by varying the physical parameters of an existing set of robotic platforms. Our results show that the proposed method can successfully adapt a trained policy to different robotic platforms with novel physical parameters and the superiority of our meta-learning algorithm compared to state-of-the-art methods for the introduced few-shot policy adaptation problem.

Deep reinforcement learning (RL) has enabled training action-selection policies, end-to-end, by learning a function which maps image pixels to action outputs. However, it's application to visuomotor robotic policy training has been limited because of the challenge of large-scale data collection when working with physical hardware. A suitable visuomotor policy should perform well not just for the task-setup it has been trained for, but also for all varieties of the task, including novel objects at different viewpoints surrounded by task-irrelevant objects. However, it is impractical for a robotic setup to sufficiently collect interactive samples in a RL framework to generalize well to novel aspects of a task. In this work, we demonstrate that by using adversarial training for domain transfer, it is possible to train visuomotor policies based on RL frameworks, and then transfer the acquired policy to other novel task domains. We propose to leverage the deep RL capabilities to learn complex visuomotor skills for uncomplicated task setups, and then exploit transfer learning to generalize to new task domains provided only still images of the task in the target domain. We evaluate our method on two real robotic tasks, picking and pouring, and compare it to a number of prior works, demonstrating its superiority.

Multi-objective reinforcement learning (MORL) is the generalization of standard reinforcement learning (RL) approaches to solve sequential decision making problems that consist of several, possibly conflicting, objectives. Generally, in such formulations, there is no single optimal policy which optimizes all the objectives simultaneously, and instead, a number of policies has to be found each optimizing a preference of the objectives. In this paper, we introduce a novel MORL approach by training a meta-policy, a policy simultaneously trained with multiple tasks sampled from a task distribution, for a number of randomly sampled Markov decision processes (MDPs). In other words, the MORL is framed as a meta-learning problem, with the task distribution given by a distribution over the preferences. We demonstrate that such a formulation results in a better approximation of the Pareto optimal solutions in terms of both the optimality and the computational efficiency. We evaluated our method on obtaining Pareto optimal policies using a number of continuous control problems with high degrees of freedom.

Information graphics are widely used to convey messages and present insights in data effectively. However, creating expressive data-driven infographics remains a great challenge for general users without design expertise. We present InfoNice, a visualization design tool that enables users to easily create data-driven infographics. InfoNice allows users to convert unembellished charts into infographics with multiple visual elements through mark customization. We implement InfoNice into Microsoft Power BI to demonstrate the integration of InfoNice into data analysis workflow seamlessly, bridging the gap between data exploration and presentation. We evaluate the usability and usefulness of InfoNice through example infographics, an in-lab user study, and real-world user feedback. Our results show that InfoNice enables users to create a variety of infographics easily for common scenarios.

Mobile robot navigation in complex and dynamic environments is a challenging but important problem. Reinforcement learning approaches fail to solve these tasks efficiently due to reward sparsities, temporal complexities and high-dimensionality of sensorimotor spaces which are inherent in such problems. We present a novel approach to train action policies to acquire navigation skills for wheel-legged robots using deep reinforcement learning. The policy maps height-map image observations to motor commands to navigate to a target position while avoiding obstacles. We propose to acquire the multifaceted navigation skill by learning and exploiting a number of manageable navigation behaviors. We also introduce a domain randomization technique to improve the versatility of the training samples. We demonstrate experimentally a significant improvement in terms of data-efficiency, success rate, robustness against irrelevant sensory data, and also the quality of the maneuver skills.

In this paper, we present a multi-sensory terrain classification algorithm with a generalized terrain representation using semantic and geometric features. We compute geometric features from lidar point clouds and extract pixel-wise semantic labels from a fully convolutional network that is trained using a dataset with a strong focus on urban navigation. We use data augmentation to overcome the biases of the original dataset and apply transfer learning to adapt the model to new semantic labels in off-road environments. Finally, we fuse the visual and geometric features using a random forest to classify the terrain traversability into three classes: safe, risky and obstacle. We implement the algorithm on our four-wheeled robot and test it in novel environments including both urban and off-road scenes which are distinct from the training environments and under summer and winter conditions. We provide experimental result to show that our algorithm can perform accurate and fast prediction of terrain traversability in a mixture of environments with a small set of training data.