In this work, we present an approach to learn cost maps for driving in complex urban environments from a very large number of demonstrations of driving behaviour by human experts. The learned cost maps are constructed directly from raw sensor measurements, bypassing the effort of manually designing cost maps as well as features. When deploying the learned cost maps, the trajectories generated not only replicate human-like driving behaviour but are also demonstrably robust against systematic errors in putative robot configuration. To achieve this we deploy a Maximum Entropy based, non-linear IRL framework which uses Fully Convolutional Neural Networks (FCNs) to represent the cost model underlying expert driving behaviour. Using a deep, parametric approach enables us to scale efficiently to large datasets and complex behaviours by being run-time independent of dataset extent during deployment. We demonstrate the scalability and the performance of the proposed approach on an ambitious dataset collected over the course of one year including more than 25k demonstration trajectories extracted from over 120km of driving around pedestrianised areas in the city of Milton Keynes, UK. We evaluate the resulting cost representations by showing the advantages over a carefully manually designed cost map and, in addition, demonstrate its robustness to systematic errors by learning precise cost-maps even in the presence of system calibration perturbations.

We present an approach for learning spatial traversability maps for driving in complex, urban environments based on an extensive dataset demonstrating the driving behaviour of human experts. The direct end-to-end mapping from raw input data to cost bypasses the effort of manually designing parts of the pipeline, exploits a large number of data samples, and can be framed additionally to refine handcrafted cost maps produced based on manual hand-engineered features. To achieve this, we introduce a maximum-entropy-based, non-linear inverse reinforcement learning (IRL) framework which exploits the capacity of fully convolutional neural networks (FCNs) to represent the cost model underlying driving behaviours. The application of a high-capacity, deep, parametric approach successfully scales to more complex environments and driving behaviours, while at deployment being run-time independent of training dataset size. After benchmarking against state-of-the-art IRL approaches, we focus on demonstrating scalability and performance on an ambitious dataset collected over the course of 1 year including more than 25,000 demonstration trajectories extracted from over 120 km of urban driving. We evaluate the resulting cost representations by showing the advantages over a carefully, manually designed cost map and furthermore demonstrate its robustness towards systematic errors by learning accurate representations even in the presence of calibration perturbations. Importantly, we demonstrate that a manually designed cost map can be refined to more accurately handle corner cases that are scarcely seen in the environment, such as stairs, slopes and underpasses, by further incorporating human priors into the training framework.

Continuous appearance shifts such as changes in weather and lighting conditions can impact the performance of deployed machine learning models. While unsupervised domain adaptation aims to address this challenge, current approaches do not utilise the continuity of the occurring shifts. In particular, many robotics applications exhibit these conditions and thus facilitate the potential to incrementally adapt a learnt model over minor shifts which integrate to massive differences over time. Our work presents an adversarial approach for lifelong, incremental domain adaptation which benefits from unsupervised alignment to a series of intermediate domains which successively diverge from the labelled source domain. We empirically demonstrate that our incremental approach improves handling of large appearance changes, e.g. day to night, on a traversable-path segmentation task compared with a direct, single alignment step approach. Furthermore, by approximating the feature distribution for the source domain with a generative adversarial network, the deployment module can be rendered fully independent of retaining potentially large amounts of the related source training data for only a minor reduction in performance.

Appearance changes due to weather and seasonal conditions represent a strong impediment to the robust implementation of machine learning systems in outdoor robotics. While supervised learning optimises a model for the training domain, it will deliver degraded performance in application domains that underlie distributional shifts caused by these changes. Traditionally, this problem has been addressed via the collection of labelled data in multiple domains or by imposing priors on the type of shift between both domains. We frame the problem in the context of unsupervised domain adaptation and develop a framework for applying adversarial techniques to adapt popular, state-of-the-art network architectures with the additional objective to align features across domains. Moreover, as adversarial training is notoriously unstable, we first perform an extensive ablation study, adapting many techniques known to stabilise generative adversarial networks, and evaluate on a surrogate classification task with the same appearance change. The distilled insights are applied to the problem of free-space segmentation for motion planning in autonomous driving. markus, bewley, ingmar@robots.ox.ac.uk ADAPTED Supervised Mapping Supervised Mapping LabelsTraining Domain Application Domains PredictionsTraining Labels Application Predictions * Performance with available training labels on the target domain. This serves as upper bound for performance.

No abstract

Learning to combine control at the level of joint torques with longer-term goal-directed behavior is a long-standing challenge for physically embodied artificial agents. Intelligent behavior in the physical world unfolds across multiple spatial and temporal scales: Although movements are ultimately executed at the level of instantaneous muscle tensions or joint torques, they must be selected to serve goals that are defined on much longer time scales and that often involve complex interactions with the environment and other agents. Recent research has demonstrated the potential of learning-based approaches applied to the respective problems of complex movement, long-term planning, and multiagent coordination. However, their integration traditionally required the design and optimization of independent subsystems and remains challenging. In this work, we tackled the integration of motor control and long-horizon decision-making in the context of simulated humanoid football, which requires agile motor control and multiagent coordination. We optimized teams of agents to play simulated football via reinforcement learning, constraining the solution space to that of plausible movements learned using human motion capture data. They were trained to maximize several environment rewards and to imitate pretrained football-specific skills if doing so led to improved performance. The result is a team of coordinated humanoid football players that exhibit complex behavior at different scales, quantified by a range of analysis and statistics, including those used in real-world sport analytics. Our work constitutes a complete demonstration of learned integrated decision-making at multiple scales in a multiagent setting.

We investigate the use of prior knowledge of human and animal movement to learn reusable locomotion skills for real legged robots. Our approach builds upon previous work on imitating human or dog Motion Capture (MoCap) data to learn a movement skill module. Once learned, this skill module can be reused for complex downstream tasks. Importantly, due to the prior imposed by the MoCap data, our approach does not require extensive reward engineering to produce sensible and natural looking behavior at the time of reuse. This makes it easy to create well-regularized, task-oriented controllers that are suitable for deployment on real robots. We demonstrate how our skill module can be used for imitation, and train controllable walking and ball dribbling policies for both the ANYmal quadruped and OP3 humanoid. These policies are then deployed on hardware via zero-shot simulation-to-reality transfer. Accompanying videos are available at https://bit.ly/robot-npmp.

Intelligent behaviour in the physical world exhibits structure at multiple spatial and temporal scales. Although movements are ultimately executed at the level of instantaneous muscle tensions or joint torques, they must be selected so as to serve goals defined on much longer timescales, and in terms of relations that extend far beyond the body itself, ultimately involving coordination with other agents. Recent research in artificial intelligence has shown the promise of learning-based approaches to the respective problems of complex movement, longer-term planning, and multi-agent coordination. However, there is limited research aimed at their integration. We study this problem by training teams of physically simulated humanoid avatars to play football in a realistic virtual environment. We develop a method that combines imitation learning, single-and multi-agent reinforcement learning and population-based training, and makes use of transferable representations of behaviour for decision making at different levels of abstraction. In a sequence of training stages, players first learn to control a fully articulated body to perform realistic, human-like movements such as running and turning; they then acquire mid-level football skills such as dribbling and shooting; finally, they develop awareness of others and learn to play as a team, successfully bridging the gap between low-level motor control at a time scale of milliseconds, and coordinated goal-directed behaviour as a team at the timescale of tens of seconds. We investigate the emergence of behaviours at different levels of abstraction, as well as the representations that underlie these behaviours using several analysis techniques, including statistics from real-world sports analytics. Our work constitutes a complete demonstration of integrated decision-making at multiple scales in a physically embodied multi-agent setting. We provide footage of the learned football skills in the supplementary video. 1