With the goal of creating efficient human-aware robot navigation systems, we present a Context-aware Model Predictive Control (MPC) formulation designed specifically for dynamic and crowded environments. State-of-the-art approaches use mainly geometric information and predictions of human motion, thus being proactive about human positions and intents but less aware of high-level behaviors encoded in contextual cues of human activities. In contrast to that, we propose a holistic planning solution that considers additional contextual information such as 3D human body poses with their velocities and recognized activities. We carefully design the MPC formulation to facilitate the integration of modern perception systems and the usage of fast solvers for embedded robot motion optimization. Compared to a set of baselines, our proposed system not only ensures safety but also significantly improves task and computational efficiency. Through extensive simulations and real-life experiments, our planner demonstrates reliable operation in terms of smooth and efficient navigation in human-populated areas.

Ensuring safe and continuous autonomous navigation in long-term mobile robot applications is still challenging. To ensure a reliable representation of the current environment without the need for periodic remapping, updating the map is recommended. However, in the case of incorrect robot pose estimation, updating the map can lead to errors that prevent the robot’s localisation and jeopardise map accuracy. In this paper, we propose a safe Lidar-based occupancy grid map-updating algorithm for dynamic environments, taking into account uncertainties in the estimation of the robot’s pose. The proposed approach allows for robust long-term operations, as it can recover the robot’s pose, even when it gets lost, to continue the map update process, providing a coherent map. Moreover, the approach is also robust to temporary changes in the map due to the presence of dynamic obstacles such as humans and other robots. Results highlighting map quality, localisation performance, and pose recovery, both in simulation and experiments, are reported.

Warehouse logistics is a rapidly growing market for robots. However, one key procedure that has not received much attention is the unwrapping of pallets to prepare them for objects picking. In fact, to prevent the goods from falling and to protect them, pallets are normally wrapped in plastic when they enter the warehouse. Currently, unwrapping is mainly performed by human operators, due to the complexity of its planning and control phases. Autonomous solutions exist, but usually they are designed for specific situations, require a large footprint and are characterized by low flexibility. In this work, we propose a novel integrated robotic solution for autonomous plastic film removal relying on an impedance-controlled robot. The main contribution is twofold: on one side, a strategy to plan Cartesian impedance and trajectory to execute the cut without damaging the goods is discussed; on the other side, we present a cutting device that we designed for this purpose. The proposed solution presents the characteristics of high versatility and the need for a reduced footprint, due to the adopted technologies and the integration with a mobile base. Experimental results are shown to validate the proposed approach.

Ensuring safe and continuous autonomous navigation in long-term mobile robot applications is still challenging. To ensure a reliable representation of the current environment without the need for periodic re-mapping, updating the map is recommended. However, in case of incorrect estimation of robot pose, updating the map can lead to errors that prevent the robot localisation and jeopardize map accuracy. In this paper, we propose a safe LIDAR-based occupancy grid map updating algorithm for dynamic environments taking into account the uncertainties in the estimation of the robot’s pose. The proposed approach allows robust long-term operations as it can recover the robot’s pose, even when it gets lost, to continue the map update process providing a coherent map. Moreover, the approach is robust also to temporary changes in the map due to the presence of dynamic obstacles such as humans and other robots. Results highlighting map quality, localisation performance, and pose recovery, both in simulation and experiments, are reported.

The objective of this paper is to propose a framework for a robot to learn multiple Sensory-Motor Contingencies from human demonstrations and reproduce them. Sensory-Motor Contingencies are a concept that describes intelligent behavior of animals and humans in relation to their environment. They have been used to design control and planning algorithms for robots capable of interacting and adapting autonomously. However, enabling a robot to autonomously develop Sensory-Motor Contingencies is challenging due to the complexity of action and perception signals. This framework leverages tools from Learning from Demonstrations to have the robot memorize various sensory phases and corresponding motor actions through an attention mechanism. This generates a metric in the perception space, used by the robot to determine which sensory-motor memory is contingent to the current context. The robot generalizes the memorized actions to adapt them to the present perception. This process creates a discrete lattice of continuous Sensory-Motor Contingencies that can control a robot in loco-manipulation tasks. Experiments on a 7-dof collaborative robotic arm with a gripper, and on a mobile manipulator demonstrate the functionality and versatility of the framework.

The growing use of mobile robots in unconventional environments demands new programming approaches to make them accessible to non-expert users. Indeed, traditional programming methods require specialized expertise in robotics and programming, limiting robots’ accessibility to a broader audience. End-user robot programming has emerged to overcome these limitations, aiming to simplify robot programming through intuitive methods. In this work, we propose a code-free approach for programming mobile robots to autonomously execute navigation tasks, i.e., reach a desired goal location from an arbitrary initial position. Our method relies on instructing the robot on new paths through demonstrations while creating and continuously updating a topometric map of the environment. Moreover, by leveraging the information gathered during the instruction phase, the robot can perceive slight environmental changes and autonomously make the best decision in response to unexpected situations (e.g., adjusting its path, stopping, or requesting user intervention). Experiments conducted in both simulated and real-world environments support the validity of our approach, as they show that the robot can successfully reach its assigned goal location in the vast majority of cases.