Institution profile

Ocado Technology

Industry researcheurope · gb
Official website
Research library2linked papers
Opportunities0open roles
Selected work

Representative Papers

Task-Conditioned Uncertainty Costmaps for Legged Locomotion

Apr 30, 2026

This work addresses the challenge of accurate foothold prediction in highly unstructured terrain, where existing methods often fail to ensure motion planning feasibility due to unreliable perception inputs. The authors propose a task-conditioned cognitive uncertainty modeling approach that integrates foothold prediction, out-of-distribution (OOD) detection, and uncertainty estimation within a unified framework to generate an uncertainty-aware cost map. This method effectively identifies OOD regions and quantifies uncertainty arising from perceptual deficiencies, even under limited training data. Experimental results demonstrate significant improvements in OOD detection performance in both simulation and real-world environments, with up to a 37% reduction in planning feasibility error compared to geometry-only baseline methods, thereby exhibiting superior reliability and robustness.

0 citationsRead paper

Stability-Aware Retargeting for Humanoid Multi-Contact Teleoperation

Oct 05, 2025

In teleoperated humanoid locomotion involving multiple non-coplanar contacts, motor torque saturation and contact sliding instability arise due to hand–surface interactions. To address this, we propose a centroidal-dynamics–based stability reorientation method. Our approach formulates and analytically derives the gradient of stability margin—enabling real-time identification and local optimization of stability-sensitive teleoperation setpoints. By dynamically adjusting contact locations and whole-body posture, it enhances motion robustness under complex multi-contact conditions. The method integrates centroidal dynamics modeling, stability margin gradient analysis, and an online reorientation algorithm, validated in both simulation and on physical hardware (e.g., Unitree H1). Experiments demonstrate significant improvements in stability margin, enhanced resilience to external disturbances, and increased joint torque headroom.

0 citationsRead paper
Recent publications

Latest Papers

Task-Conditioned Uncertainty Costmaps for Legged Locomotion

Apr 30, 2026

This work addresses the challenge of accurate foothold prediction in highly unstructured terrain, where existing methods often fail to ensure motion planning feasibility due to unreliable perception inputs. The authors propose a task-conditioned cognitive uncertainty modeling approach that integrates foothold prediction, out-of-distribution (OOD) detection, and uncertainty estimation within a unified framework to generate an uncertainty-aware cost map. This method effectively identifies OOD regions and quantifies uncertainty arising from perceptual deficiencies, even under limited training data. Experimental results demonstrate significant improvements in OOD detection performance in both simulation and real-world environments, with up to a 37% reduction in planning feasibility error compared to geometry-only baseline methods, thereby exhibiting superior reliability and robustness.

0 citationsRead paper

Stability-Aware Retargeting for Humanoid Multi-Contact Teleoperation

Oct 05, 2025

In teleoperated humanoid locomotion involving multiple non-coplanar contacts, motor torque saturation and contact sliding instability arise due to hand–surface interactions. To address this, we propose a centroidal-dynamics–based stability reorientation method. Our approach formulates and analytically derives the gradient of stability margin—enabling real-time identification and local optimization of stability-sensitive teleoperation setpoints. By dynamically adjusting contact locations and whole-body posture, it enhances motion robustness under complex multi-contact conditions. The method integrates centroidal dynamics modeling, stability margin gradient analysis, and an online reorientation algorithm, validated in both simulation and on physical hardware (e.g., Unitree H1). Experiments demonstrate significant improvements in stability margin, enhanced resilience to external disturbances, and increased joint torque headroom.

0 citationsRead paper