This paper presents a three-layered architecture that enables stylistic locomotion with online contact location adjustment. Our method combines an autoregressive Deep Neural Network (DNN) acting as a trajectory generation layer with a model-based trajectory adjustment and trajectory control layers. The DNN produces centroidal and postural references serving as an initial guess and regularizer for the other layers. Being the DNN trained on human motion capture data, the resulting robot motion exhibits locomotion patterns, resembling a human walking style. The trajectory adjustment layer utilizes non-linear optimization to ensure dynamically feasible center of mass (CoM) motion while addressing step adjustments. We compare two implementations of the trajectory adjustment layer: one as a receding horizon planner (RHP) and the other as a model predictive controller (MPC). To enhance MPC performance, we introduce a Kalman filter to reduce measurement noise. The filter parameters are automatically tuned with a Genetic Algorithm. Experimental results on the ergoCub humanoid robot demonstrate the system's ability to prevent falls, replicate human walking styles, and withstand disturbances up to 68 Newton. Website: https://sites.google.com/view/dnn-mpc-walking Youtube video: https://www.youtube.com/watch?v=x3tzEfxO-xQ

We present an avatar system designed to facilitate the embodiment of humanoid robots by human operators, validated through iCub3, a humanoid developed at the Istituto Italiano di Tecnologia (IIT). More precisely, the contribution of the paper is twofold: first, we present the humanoid iCub3 as a robotic avatar which integrates the latest significant improvements after about fifteen years of development of the iCub series; second, we present a versatile avatar system enabling humans to embody humanoid robots encompassing aspects such as locomotion, manipulation, voice, and face expressions with comprehensive sensory feedback including visual, auditory, haptic, weight, and touch modalities. We validate the system by implementing several avatar architecture instances, each tailored to specific requirements. First, we evaluated the optimized architecture for verbal, non-verbal, and physical interactions with a remote recipient. This testing involved the operator in Genoa and the avatar in the Biennale di Venezia, Venice - about 290 Km away - thus allowing the operator to visit remotely the Italian art exhibition. Second, we evaluated the optimised architecture for recipient physical collaboration and public engagement on-stage, live, at the We Make Future show, a prominent world digital innovation festival. In this instance, the operator was situated in Genoa while the avatar operates in Rimini - about 300 Km away - interacting with a recipient who entrusted the avatar a payload to carry on stage before an audience of approximately 2000 spectators. Third, we present the architecture implemented by the iCub Team for the ANA Avatar XPrize competition.

Robot multimodal locomotion encompasses the ability to transition between walking and flying, representing a significant challenge in robotics. This work presents an approach that enables automatic smooth transitions between legged and aerial locomotion. Leveraging the concept of Adversarial Motion Priors, our method allows the robot to imitate motion datasets and accomplish the desired task without the need for complex reward functions. The robot learns walking patterns from human-like gaits and aerial locomotion patterns from motions obtained using trajectory optimization. Through this process, the robot adapts the locomotion scheme based on environmental feedback using reinforcement learning, with the spontaneous emergence of mode-switching behavior. The results highlight the potential for achieving multimodal locomotion in aerial humanoid robotics through automatic control of walking and flying modes, paving the way for applications in diverse domains such as search and rescue, surveillance, and exploration missions. This research contributes to advancing the capabilities of aerial humanoid robots in terms of versatile locomotion in various environments.

Balancing and push-recovery are essential capabilities enabling humanoid robots to solve complex locomotion tasks. In this context, classical control systems tend to be based on simplified physical models and hard-coded strategies. Although successful in specific scenarios, this approach requires demanding tuning of parameters and switching logic between specifically-designed controllers for handling more general perturbations. We apply model-free Deep Reinforcement Learning for training a general and robust humanoid push-recovery policy in a simulation environment. Our method targets high-dimensional whole-body humanoid control and is validated on the iCub humanoid. Reward components incorporating expert knowledge on humanoid control enable fast learning of several robust behaviors by the same policy, spanning the entire body. We validate our method with extensive quantitative analyses in simulation, including out-of-sample tasks which demonstrate policy robustness and generalization, both key requirements towards real-world robot deployment.