Learning Forward Dynamics Model and Informed Trajectory Sampler for Safe Quadruped Navigation

Kim, Yun‐Ho; Kim, Chanyoung; Hwangbo, Jemin

doi:10.15607/rss.2022.xviii.069

Cited by 7 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Focused on the works based on model-free RL, we extract essential design choices and conduct a comparative analysis with our approach. It's noteworthy that alternative methodologies also exist, including those based on offline RL or model-based RL [55][56][57]. For instance, Kahn et al [55,56] showed outdoor navigation using an offline-trained dynamics model combined with a sampling-based planner.…”

Section: Comparison To Related Work and Validation Of Our Methodsmentioning

confidence: 99%

Learning robust autonomous navigation and locomotion for wheeled-legged robots

Lee,

Bjelonic,

Reske

et al. 2024

Sci. Robot.

View full text Add to dashboard Cite

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.

show abstract

Section: Comparison To Related Work and Validation Of Our Methodsmentioning

confidence: 99%

Learning robust autonomous navigation and locomotion for wheeled-legged robots

Lee,

Bjelonic,

Reske

et al. 2024

Sci. Robot.

View full text Add to dashboard Cite

show abstract

“…Complementary, learned dynamics models from real-world data are capable of accounting for unmodeled effects in simulation and are used for planning. (Kahn et al, 2021) and (Kim et al, 2022) learn a forward dynamics model, where (Kahn et al, 2021) predict future events and states of the robot from real-world data, and (Kim et al, 2022) use a simulation to collect data. (Xiao et al, 2021) learn the inverse kinodynamics model of a wheeled robot from proprioception and (Karnan et al, 2022) expand this concept by conditioning the model on visual data of future terrain patches to anticipate terrain interaction.…”

Section: Other Traversability Estimation Approachesmentioning

confidence: 99%

Locomotion Policy Guided Traversability Learning using Volumetric Representations of Complex Environments

Frey¹,

Hoeller²,

Khattak³

et al. 2022

2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Autonomous navigation at high speeds in off-road environments necessitates robots to comprehensively understand their surroundings using onboard sensing only. The extreme conditions posed by the off-road setting can cause degraded camera image quality due to poor lighting and motion blur, as well as limited sparse geometric information available from LiDAR sensing when driving at high speeds. In this work, we present RoadRunner, a novel framework capable of predicting terrain traversability and an elevation map directly from camera and LiDAR sensor inputs. RoadRunner enables reliable autonomous navigation, by fusing sensory information, handling of uncertainty, and generation of contextually informed predictions about the geometry and traversability of the terrain while operating at low latency. In contrast to existing methods relying on classifying handcrafted semantic classes and using heuristics to predict traversability costs, our method is trained end-to-end in a self-supervised fashion. The RoadRunner network architecture builds upon popular sensor fusion network architectures from the autonomous driving domain, which embed LiDAR and camera information into a common Bird's Eye View perspective. Training is enabled by utilizing an existing traversability estimation stack to generate training data in hindsight in a scalable manner from realworld off-road driving datasets. Furthermore, RoadRunner improves the system latency by a factor of ∼ 4, from 500 ms to 140 ms, while improving the accuracy for traversability costs and elevation map predictions. We demonstrate the effectiveness of RoadRunner in enabling safe and reliable offroad navigation at high speeds in multiple real-world driving scenarios through unstructured desert environments.

show abstract