LEVA: A high-mobility logistic vehicle with legged suspension

📅 2025-03-13
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
To address key bottlenecks in autonomous logistics transport—namely, poor maneuverability, low payload capacity, and weak obstacle-crossing capability—on complex unstructured terrains (e.g., farmland, construction sites, disaster zones), this work proposes LEVA, a wheel-leg hybrid unmanned cargo platform. Methodologically, LEVA integrates four core innovations: (1) a novel parallel-mechanism-based legged suspension system; (2) reinforcement learning–driven autonomous stair negotiation; (3) an omnidirectional active-steering wheeled locomotion system; and (4) a mechatronic adaptive cargo-box grasping mechanism, all embedded within a multimodal terrain perception and motion planning framework. Experimentally, LEVA achieves an 85 kg payload, stable all-terrain mobility—including stairs, slopes, and uneven ground—fully automated loading/unloading, and ultra-low energy consumption (Cost of Transport = 0.15). Comparative evaluations demonstrate significantly superior obstacle traversal performance and operational reliability over state-of-the-art wheeled and tracked logistics robots, establishing a deployable paradigm for autonomous transport in agriculture, infrastructure, and emergency response applications.

Technology Category

Application Category

📝 Abstract
The autonomous transportation of materials over challenging terrain is a challenge with major economic implications and remains unsolved. This paper introduces LEVA, a high-payload, high-mobility robot designed for autonomous logistics across varied terrains, including those typical in agriculture, construction, and search and rescue operations. LEVA uniquely integrates an advanced legged suspension system using parallel kinematics. It is capable of traversing stairs using a rl controller, has steerable wheels, and includes a specialized box pickup mechanism that enables autonomous payload loading as well as precise and reliable cargo transportation of up to 85 kg across uneven surfaces, steps and inclines while maintaining a cot of as low as 0.15. Through extensive experimental validation, LEVA demonstrates its off-road capabilities and reliability regarding payload loading and transport.
Problem

Research questions and friction points this paper is trying to address.

Autonomous material transport over challenging terrain.
High-payload robot for logistics in agriculture, construction, and rescue.
Legged suspension system for reliable cargo transport on uneven surfaces.
Innovation

Methods, ideas, or system contributions that make the work stand out.

Advanced legged suspension with parallel kinematics
RL controller for stair traversal and steerable wheels
Specialized box pickup mechanism for autonomous loading
🔎 Similar Papers
No similar papers found.
M
Marco Arnold
Robotic Systems Lab, ETH Zürich, 8092 Zürich, Switzerland
L
Lukas Hildebrandt
Robotic Systems Lab, ETH Zürich, 8092 Zürich, Switzerland
K
Kaspar Janssen
Robotic Systems Lab, ETH Zürich, 8092 Zürich, Switzerland
E
Efe Ongan
Robotic Systems Lab, ETH Zürich, 8092 Zürich, Switzerland
P
Pascal Burge
Zurich School of Applied Sciences
'
'Ad'am Gyula G'abriel
Robotic Systems Lab, ETH Zürich, 8092 Zürich, Switzerland
James Kennedy
James Kennedy
Robotic Systems Lab, ETH Zürich, 8092 Zürich, Switzerland
R
Rishi Lolla
Robotic Systems Lab, ETH Zürich, 8092 Zürich, Switzerland
Q
Quanisha Oppliger
Zurich School of Applied Sciences
M
Micha Schaaf
Zurich School of Applied Sciences
J
Joseph Church
Robotic Systems Lab, ETH Zürich, 8092 Zürich, Switzerland
M
Michael Fritsche
Robotic Systems Lab, ETH Zürich, 8092 Zürich, Switzerland
Victor Klemm
Victor Klemm
PhD Student at Robotic Systems Lab, ETH Zurich
Robotics
Turcan Tuna
Turcan Tuna
ETH Zurich, Robotics Systems Lab
RoboticsRobust LocalizationVisual Inertial OdometryComputer VisionSLAM
G
Giorgio Valsecchi
Robotic Systems Lab, ETH Zürich, 8092 Zürich, Switzerland
C
Cedric Weibel
Robotic Systems Lab, ETH Zürich, 8092 Zürich, Switzerland
Marco Hutter
Marco Hutter
Professor of Robotics, ETH Zurich
Legged RoboticsRoboticsControl