“…where R b (3,3) is the last element of the rotation matrix representation of the body orientation. We also motivated the policy to keep the height of the robot's base above the ground (h base ) around 0.55 m with the tolerance of 0.05 m:…”
Section: High-level Policy Rewardsmentioning
confidence: 99%
“…Traditional wheeled robots cannot surmount these obstacles effectively, and legged systems alone are inadequate in achieving the necessary velocity and efficiency. For instance, the ANYmal robot [1] can only operate for a maximum of 1 hour [2,3] at half the speed of an average human walking (2.2 km/h on average [4]).…”
Autonomous wheeled-legged robots have the potential to transform logistics systems, improving operational efficiency and adaptability in urban environments. Navigating urban environments, however, poses unique challenges for robots, necessitating innovative solutions for locomotion and navigation. These challenges include the need for adaptive locomotion across varied terrains and the ability to navigate efficiently around complex dynamic obstacles. This work introduces a fully integrated system comprising adaptive locomotion control, mobility-aware local navigation planning, and large-scale path planning within the city. Using model-free reinforcement learning (RL) techniques and privileged learning, we developed a versatile locomotion controller. This controller achieves efficient and robust locomotion over various rough terrains, facilitated by smooth transitions between walking and driving modes. It is tightly integrated with a learned navigation controller through a hierarchical RL framework, enabling effective navigation through challenging terrain and various obstacles at high speed. Our controllers are integrated into a large-scale urban navigation system and validated by autonomous, kilometer-scale navigation missions conducted in Zurich, Switzerland, and Seville, Spain. These missions demonstrate the system’s robustness and adaptability, underscoring the importance of integrated control systems in achieving seamless navigation in complex environments. Our findings support the feasibility of wheeled-legged robots and hierarchical RL for autonomous navigation, with implications for last-mile delivery and beyond.
“…where R b (3,3) is the last element of the rotation matrix representation of the body orientation. We also motivated the policy to keep the height of the robot's base above the ground (h base ) around 0.55 m with the tolerance of 0.05 m:…”
Section: High-level Policy Rewardsmentioning
confidence: 99%
“…Traditional wheeled robots cannot surmount these obstacles effectively, and legged systems alone are inadequate in achieving the necessary velocity and efficiency. For instance, the ANYmal robot [1] can only operate for a maximum of 1 hour [2,3] at half the speed of an average human walking (2.2 km/h on average [4]).…”
Autonomous wheeled-legged robots have the potential to transform logistics systems, improving operational efficiency and adaptability in urban environments. Navigating urban environments, however, poses unique challenges for robots, necessitating innovative solutions for locomotion and navigation. These challenges include the need for adaptive locomotion across varied terrains and the ability to navigate efficiently around complex dynamic obstacles. This work introduces a fully integrated system comprising adaptive locomotion control, mobility-aware local navigation planning, and large-scale path planning within the city. Using model-free reinforcement learning (RL) techniques and privileged learning, we developed a versatile locomotion controller. This controller achieves efficient and robust locomotion over various rough terrains, facilitated by smooth transitions between walking and driving modes. It is tightly integrated with a learned navigation controller through a hierarchical RL framework, enabling effective navigation through challenging terrain and various obstacles at high speed. Our controllers are integrated into a large-scale urban navigation system and validated by autonomous, kilometer-scale navigation missions conducted in Zurich, Switzerland, and Seville, Spain. These missions demonstrate the system’s robustness and adaptability, underscoring the importance of integrated control systems in achieving seamless navigation in complex environments. Our findings support the feasibility of wheeled-legged robots and hierarchical RL for autonomous navigation, with implications for last-mile delivery and beyond.
Designing actuators that can modulate power, achieve high energy efficiency, and ensure safe collision remains a challenge, especially for dynamic energy robot systems (DERS) with high‐performance requirements. Herein, a novel multi‐configuration elastic actuator (MCEA) is proposed based on a controllable planetary differential mechanism (PDM) with one power port from three springs. These springs, positioned between the inner gear ring and the fixed housing shell, are regulated by a single servo motor through a ratchet–pawl mechanism. This setup enables the springs to absorb energy during collisions, reducing impact and subsequently releasing this energy to boost power output. The inner gear ring functions as a controllable one‐way rotating element, acting either as an input or output for power. The MCEA's ability to manage power modulation and energy flow is demonstrated through experiments that highlight its potential for safe collision management, energy recycling, and power modulation. Experiment results indicate that the maximum output power of the MCEA in the proposed hybrid elastic actuation (HEA) mode is 8.05 times higher than that in the traditional actuation (TA) mode. A single‐legged robot with a four‐link mechanism is also built to validate the considerable performance in the application of legged robots, showing considerable adaptability and prospects for DERS.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.