Abstract-This paper introduces a cognitive architecture for a humanoid robot to engage in a proactive, mixed-initiative exploration and manipulation of its environment, where the initiative can originate from both the human and the robot. The framework, based on a biologically-grounded theory of the brain and mind, integrates a reactive interaction engine, a number of state-of-the art perceptual and motor learning algorithms, as well as planning abilities and an autobiographical memory. The architecture as a whole drives the robot behavior to solve the symbol grounding problem, acquire language capabilities, execute goal-oriented behavior, and express a verbal narrative of its own experience in the world. We validate our approach in humanrobot interaction experiments with the iCub humanoid robot, showing that the proposed cognitive architecture can be applied in real time within a realistic scenario and that it can be used with naive users.

Internal models play a key role in cognitive agents by providing on the one hand predictions of sensory consequences of motor commands (forward models), and on the other hand inverse mappings (inverse models) to realise tasks involving control loops, such as imitation tasks. The ability to predict and generate new actions in continuously evolving environments intrinsically requiring the use of different sensory modalities is particularly relevant for autonomous robots, which must also be able to adapt their models online. We present a learning architecture based on self-learned multimodal sensorimotor representations. To attain accurate forward models, we propose an online heterogeneous ensemble learning method that allows us to improve the prediction accuracy by leveraging differences of multiple diverse predictors. We further propose a method to learn inverse models on-the-fly to equip a robot with multimodal learning skills to perform imitation tasks using multiple sensory modalities. We have evaluated the proposed methods on an iCub humanoid robot. Since no assumptions are made on the robot kinematic/dynamic structure, the method can be applied to different robotic platforms.

Similar to humans, robots benefit from interacting with their environment through a number of different sensor modalities, such as vision, touch, sound. However, learning from different sensor modalities is difficult, because the learning model must be able to handle diverse types of signals, and learn a coherent representation even when parts of the sensor inputs are missing. In this paper, a multimodal variational autoencoder is proposed to enable an iCub humanoid robot to learn representations of its sensorimotor capabilities from different sensor modalities. The proposed model is able to (1) reconstruct missing sensory modalities, (2) predict the sensorimotor state of self and the visual trajectories of other agents actions, and (3) control the agent to imitate an observed visual trajectory. Also, the proposed multimodal variational autoencoder can capture the kinematic redundancy of the robot motion through the learned probability distribution. Training multimodal models is not trivial due to the combinatorial complexity given by the possibility of missing modalities. We propose a strategy to train multimodal models, which successfully achieves improved performance of different reconstruction models. Finally, extensive experiments have been carried out using an iCub humanoid robot, showing high performance in multiple reconstruction, prediction and imitation tasks.

In this paper, we present a novel framework for finding the kinematic structure correspondence between two objects in videos via hypergraph matching. In contrast to prior appearance and graph alignment based matching methods which have been applied among two similar static images, the proposed method finds correspondences between two dynamic kinematic structures of heterogeneous objects in videos. Our main contributions can be summarised as follows: (i) casting the kinematic structure correspondence problem into a hypergraph matching problem, incorporating multi-order similarities with normalising weights, (ii) a structural topology similarity measure by a new topology constrained subgraph isomorphism aggregation, (iii) a kinematic correlation measure between pairwise nodes, and (iv) a combinatorial local motion similarity measure using geodesic distance on the Riemannian manifold. We demonstrate the robustness and accuracy of our method through a number of experiments on complex articulated synthetic and real data.

Abstract-Although many tasks intrinsically involve multiple modalities, often only data from a single modality are used to improve complex robots acquisition of new skills. We present a method to equip robots with multimodal learning skills to achieve multimodal imitation on-the-fly on multiple concurrent task spaces, including vision, touch and proprioception, only using self-learned multimodal sensorimotor relations, without the need of solving inverse kinematic problems or explicit analytical models formulation. We evaluate the proposed method on a humanoid iCub robot learning to interact with a piano keyboard and imitating a human demonstration. Since no assumptions are made on the kinematic structure of the robot, the method can be also applied to different robotic platforms.