Generative navigation policies have made rapid progress in improving end-to-end learned navigation. Despite their promising results, this paradigm has two structural problems. First, the sampled trajectories exist in an abstract, unscaled space without metric grounding. Second, the control strategy discards the full path, instead moving directly towards a single waypoint. This leads to short-sighted and unsafe actions, moving the robot towards obstacles that a complete and correctly scaled path would circumvent. To address these issues, we propose MetricNet, an effective add-on for generative navigation that predicts the metric distance between waypoints, grounding policy outputs in real-world coordinates. We evaluate our method in simulation with a new benchmarking framework and show that executing MetricNet-scaled waypoints significantly improves both navigation and exploration performance. Beyond simulation, we further validate our approach in real-world experiments. Finally, we propose MetricNav, which integrates MetricNet into a navigation policy to guide the robot away from obstacles while still moving towards the goal.

This paper presents a scheme to enhance payload manipulation using a robot collaborating with an overhead crane. In the current industrial practice, when the crane's payload has to be accurately manipulated and located in a desired position, the task becomes laborious and risky since the operators have to guide the fine motions of the payload by hand. In the proposed collaborative scheme, the crane lifts the payload while the robot's end-effector guides it toward the desired position. The only link between the robot and the crane is the interaction force produced during the guiding of the payload. Two admittance transfer functions are considered to accomplish harmless and smooth contact with the payload. The first is used in a position-based admittance control integrated with the robot. The second one adds compliance to the crane by processing the interaction force through the admittance transfer function to generate a crane's velocity command that makes the crane follow the payload. Then the robot's end-effector and the crane move collaboratively to guide the payload to the desired location. A method is presented to design the admittance controllers that accomplish a fluent robot-crane collaboration. Simulations and experiments validating the scheme potential are shown.

Nowadays, robots are applied in dynamic environments. For a robust operation, the motion planning module must consider other tasks besides reaching a specified pose: (self) collision avoidance, joint limit avoidance, keeping an advantageous configuration, etc. Each task demands different joint control commands, which may counteract each other. We present a hierarchical control that, depending on the robot and environment state, determines online a suitable priority among those tasks. Thereby, the control command of a lower-prioritized task never hinders the control command of a higher-prioritized task. We ensure smooth control signals also during priority rearrangement. Our hierarchical control computes reference joint velocities. However, the underlying concepts of hierarchical control differ when using joint accelerations or joint torques as control signals instead. So, as a further contribution, we provide a comprehensive discussion on how joint velocity control, joint acceleration control, and joint torque control differ in hierarchical task control. We validate our formulation in an experiment on hardware.

Unmanned aerial vehicle (UAV)-assisted sensor networks (UASNets), which play a crucial role in creating new opportunities, are experiencing significant growth in civil applications worldwide. UASNets improve disaster management through timely surveillance and advance precision agriculture with detailed crop monitoring, thereby significantly transforming the commercial economy. UASNets revolutionize the commercial sector by offering greater efficiency, safety, and cost-effectiveness, highlighting their transformative impact. A fundamental aspect of these new capabilities and changes is the collection of data from rugged and remote areas. Due to their excellent mobility and maneuverability, UAVs are employed to collect data from ground sensors in harsh environments, such as natural disaster monitoring, border surveillance, and emergency response monitoring. One major challenge in these scenarios is that the movements of UAVs affect channel conditions and result in packet loss. Fast movements of UAVs lead to poor channel conditions and rapid signal degradation, resulting in packet loss. On the other hand, slow mobility of a UAV can cause buffer overflows of the ground sensors, as newly arrived data is not promptly collected by the UAV. Our proposal to address this challenge is to minimize packet loss by jointly optimizing the velocity controls and data collection schedules of multiple UAVs.Furthermore, in UASNets, swift movements of UAVs result in poor channel conditions and fast signal attenuation, leading to an extended age of information (AoI). In contrast, slow movements of UAVs prolong flight time, thereby extending the AoI of ground sensors.To address this challenge, we propose a new mean-field flight resource allocation optimization to minimize the AoI of sensory data.

This paper introduces Diffusion Policy, a new way of generating robot behavior by representing a robot's visuomotor policy as a conditional denoising diffusion process. We benchmark Diffusion Policy across 12 different tasks from 4 different robot manipulation benchmarks and find that it consistently outperforms existing state-of-the-art robot learning methods with an average improvement of 46.9%. Diffusion Policy learns the gradient of the action-distribution score function and iteratively optimizes with respect to this gradient field during inference via a series of stochastic Langevin dynamics steps. We find that the diffusion formulation yields powerful advantages when used for robot policies, including gracefully handling multimodal action distributions, being suitable for high-dimensional action spaces, and exhibiting impressive training stability. To fully unlock the potential of diffusion models for visuomotor policy learning on physical robots, this paper presents a set of key technical contributions including the incorporation of receding horizon control, visual conditioning, and the time-series diffusion transformer. We hope this work will help motivate a new generation of policy learning techniques that are able to leverage the powerful generative modeling capabilities of diffusion models. Code, data, and training details will be publicly available.

Machine Learning methods, such as those from the Reinforcement Learning (RL) literature, have increasingly been applied to robot control problems. However, such control methods, even when learning environment dynamics (e.g. as in Model-Based RL/control) often remain data-inefficient. Furthermore, the decisions made by learned policies or the estimations made by learned dynamic models, unlike those made by their hand-designed counterparts, are not readily interpretable by a human user without the use of Explainable AI techniques. This has several disadvantages, such as increased difficulty both in debugging and integration in safety-critical systems. On the other hand, in many robotic systems, prior knowledge of environment kinematics and dynamics is at least partially available (e.g. from classical mechanics). Arguably, incorporating such priors to the environment model or decision process can help address the aforementioned problems: it reduces problem complexity and the needs in terms of exploration, while also facilitating the expression of the decisions taken by the agent in terms of physically meaningful entities. Our aim with this paper is to illustrate and support this point of view. We model a payload manipulation problem based on a real robotic system, and show that leveraging prior knowledge about the dynamics of the environment can lead to improved explainability and an increase in both safety and data-efficiency,leading to satisfying generalization properties with less data.

This work developed a kernel-based residual learning framework for quadrupedal robotic locomotion. Initially, a kernel neural network is trained with data collected from an MPC controller. Alongside a frozen kernel network, a residual controller network is trained via reinforcement learning to acquire generalized locomotion skills and resilience against external perturbations. With this proposed framework, a robust quadrupedal locomotion controller is learned with high sample efficiency and controllability, providing omnidirectional locomotion at continuous velocities. Its versatility and robustness are validated on unseen terrains that the expert MPC controller fails to traverse. Furthermore, the learned kernel can produce a range of functional locomotion behaviors and can generalize to unseen gaits.

A model used for velocity control during car following was proposed based on deep reinforcement learning (RL). To fulfil the multi-objectives of car following, a reward function reflecting driving safety, efficiency, and comfort was constructed. With the reward function, the RL agent learns to control vehicle speed in a fashion that maximizes cumulative rewards, through trials and errors in the simulation environment. A total of 1,341 car-following events extracted from the Next Generation Simulation (NGSIM) dataset were used to train the model. Car-following behavior produced by the model were compared with that observed in the empirical NGSIM data, to demonstrate the model's ability to follow a lead vehicle safely, efficiently, and comfortably. Results show that the model demonstrates the capability of safe, efficient, and comfortable velocity control in that it 1) has small percentages (8\%) of dangerous minimum time to collision values (\textless\ 5s) than human drivers in the NGSIM data (35\%); 2) can maintain efficient and safe headways in the range of 1s to 2s; and 3) can follow the lead vehicle comfortably with smooth acceleration. The results indicate that reinforcement learning methods could contribute to the development of autonomous driving systems.