A bipedal walking robot that can fly, slackline, and skateboard

Kim, Kyunam; Spieler, Patrick; Lupu, Elena-Sorina; Ramezani, Alireza; Chung, Soon‐Jo

doi:10.1126/scirobotics.abf8136

Cited by 100 publications

(47 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When walking at 1.0m/s, using a total of 200 watts of power, while performing different locomotion behaviours such as squatting, the calculated COT was 0.7. For the LEO robot, v = 0.2 m/s COT = 108 was determined during walking [137]. When walking on the ground, LEO sucks down 544 watts, of which 445 watts go to the propellers and 99 watts are used by the electronics and legs [137].…”

Section: Energy Efficiency Of the Walking Robot's Motionmentioning

confidence: 99%

See 1 more Smart Citation

Recent Advances in Bipedal Walking Robots: Review of Gait, Drive, Sensors and Control Systems

Mikołajczyk

Mikołajewska

Al-Shuka

et al. 2022

Sensors

View full text Add to dashboard Cite

Currently, there is an intensive development of bipedal walking robots. The most known solutions are based on the use of the principles of human gait created in nature during evolution. Modernbipedal robots are also based on the locomotion manners of birds. This review presents the current state of the art of bipedal walking robots based on natural bipedal movements (human and bird) as well as on innovative synthetic solutions. Firstly, an overview of the scientific analysis of human gait is provided as a basis for the design of bipedal robots. The full human gait cycle that consists of two main phases is analysed and the attention is paid to the problem of balance and stability, especially in the single support phase when the bipedal movement is unstable. The influences of passive or active gait on energy demand are also discussed. Most studies are explored based on the zero moment. Furthermore, a review of the knowledge on the specific locomotor characteristics of birds, whose kinematics are derived from dinosaurs and provide them with both walking and running abilities, is presented. Secondly, many types of bipedal robot solutions are reviewed, which include nature-inspired robots (human-like and birdlike robots) and innovative robots using new heuristic, synthetic ideas for locomotion. Totally 45 robotic solutions are gathered by thebibliographic search method. Atlas was mentioned as one of the most perfect human-like robots, while the birdlike robot cases were Cassie and Digit. Innovative robots are presented, such asslider robot without knees, robots with rotating feet (3 and 4 degrees of freedom), and the hybrid robot Leo, which can walk on surfaces and fly. In particular, the paper describes in detail the robots’ propulsion systems (electric, hydraulic), the structure of the lower limb (serial, parallel, mixed mechanisms), the types and structures of control and sensor systems, and the energy efficiency of the robots. Terrain roughness recognition systems using different sensor systems based on light detection and ranging or multiple cameras are introduced. A comparison of performance, control and sensor systems, drive systems, and achievements of known human-like and birdlike robots is provided. Thirdly, for the first time, the review comments on the future of bipedal robots in relation to the concepts of conventional (natural bipedal) and synthetic unconventional gait. We critically assess and compare prospective directions for further research that involve the development of navigation systems, artificial intelligence, collaboration with humans, areas for the development of bipedal robot applications in everyday life, therapy, and industry.

show abstract

Section: Energy Efficiency Of the Walking Robot's Motionmentioning

confidence: 99%

“…A robot called LEONARDO (LEgsONboARDdrOne), or LEO for short, is a versatile design that enables two main modes of movement walking as well as flying [137]. This robot presents synchronized agile walking movements interspersed with flight manoeuvres.…”

mentioning

confidence: 99%

Recent Advances in Bipedal Walking Robots: Review of Gait, Drive, Sensors and Control Systems

Mikołajczyk

Mikołajewska

Al-Shuka

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…This demonstrates the generalizability of the proposed method running on different quadrotors. Moreover, our control algorithm is formulated generally for all robotic systems described by the Euler-Langrange equation (see "Materials and Methods"), including many types of aircraft such as [21,48].…”

Section: Generalization To New Trajectories and New Aircraftmentioning

confidence: 99%

Neural-Fly enables rapid learning for agile flight in strong winds

O’Connell

Shi

et al. 2022

Sci. Robot.

Self Cite

View full text Add to dashboard Cite

Executing safe and precise flight maneuvers in dynamic high-speed winds is important for the ongoing commoditization of uninhabited aerial vehicles (UAVs). However, because the relationship between various wind conditions and its effect on aircraft maneuverability is not well understood, it is challenging to design effective robot controllers using traditional control design methods. We present Neural-Fly, a learning-based approach that allows rapid online adaptation by incorporating pretrained representations through deep learning. Neural-Fly builds on two key observations that aerodynamics in different wind conditions share a common representation and that the wind-specific part lies in a low-dimensional space. To that end, Neural-Fly uses a proposed learning algorithm, domain adversarially invariant meta-learning (DAIML), to learn the shared representation, only using 12 minutes of flight data. With the learned representation as a basis, Neural-Fly then uses a composite adaptation law to update a set of linear coefficients for mixing the basis elements. When evaluated under challenging wind conditions generated with the Caltech Real Weather Wind Tunnel, with wind speeds up to 43.6 kilometers/hour (12.1 meters/second), Neural-Fly achieves precise flight control with substantially smaller tracking error than stateof-the-art nonlinear and adaptive controllers. In addition to strong empirical performance, the exponential stability of Neural-Fly results in robustness guarantees. Last, our control design extrapolates to unseen wind conditions, is shown to be effective for outdoor flights with only onboard sensors, and can transfer across drones with minimal performance degradation.

show abstract

“…The development of the hardware has enabled quadrupedal robots to perform agile motor skills while maintaining high stability [55,27,7]. On the other hand, the development of bipedal robots has focused on the robustness of locomotion [6,75,33]. Traditionally, designing effective motion controllers involves a lot of manual engineering and domain expertise.…”

Section: Related Work a Legged Robot Controlmentioning

confidence: 99%

Human Motion Control of Quadrupedal Robots using Deep Reinforcement Learning

Kim¹,

Sorokin²,

Lee³

et al. 2022

Preprint

View full text Add to dashboard Cite

A motion-based control interface promises flexible robot operations in dangerous environments by combining user intuitions with the robot's motor capabilities. However, designing a motion interface for non-humanoid robots, such as quadrupeds or hexapods, is not straightforward because different dynamics and control strategies govern their movements. We propose a novel motion control system that allows a human user to operate various motor tasks seamlessly on a quadrupedal robot. We first retarget the captured human motion into the corresponding robot motion with proper semantics using supervised learning and post-processing techniques. Then we apply the motion imitation learning with curriculum learning to develop a control policy that can track the given retargeted reference. We further improve the performance of both motion retargeting and motion imitation by training a set of experts. As we demonstrate, a user can execute various motor tasks using our system, including standing, sitting, tilting, manipulating, walking, and turning, on simulated and real quadrupeds. We also conduct a set of studies to analyze the performance gain induced by each component.(Video 1

show abstract

A bipedal walking robot that can fly, slackline, and skateboard

Abstract: Synchronized control of propellers and legs enables a bipedal robot to fly, slackline, and skateboard.

Cited by 100 publications

References 71 publications

Recent Advances in Bipedal Walking Robots: Review of Gait, Drive, Sensors and Control Systems

Recent Advances in Bipedal Walking Robots: Review of Gait, Drive, Sensors and Control Systems

Neural-Fly enables rapid learning for agile flight in strong winds

Human Motion Control of Quadrupedal Robots using Deep Reinforcement Learning

Contact Info

Product

Resources

About