aiqbench analysis
This research introduces Adaptive-MHE, an online system identification framework that enables legged robots to adaptively estimate environmental parameters like mass and friction during loco-manipulation tasks. By coupling sampling-based estimation with model predictive control, the method effectively bridges the sim-to-real gap without relying on differentiable dynamics assumptions common in classical approaches. The results demonstrate that this adaptive strategy matches the performance of controllers with perfect ground-truth knowledge, offering a robust solution for uncertain physical environments.
Adaptive-MHE: A Sampling-Based Adaptive MPC for Legged Loco-Manipulation via Moving Horizon Estimation
arXiv:2609.17832v1 Announce Type: new Abstract: Legged robots have demonstrated a remarkable ability to traverse various terrains, yet generating effective loco-manipulation behaviors remains challenging. A key difficulty is that object and terrain parameters are typically unknown to the robot, and mismatches between these parameters and their simulated counterparts introduce a sim-to-real gap that degrades control performance. Classical system identification (Sys-ID) methods often assume differentiable dynamics, an assumption that does not hold for contact-rich legged systems. Sampling-based Sys-ID avoids this restriction by directly matching simulated and recorded state trajectories through massively parallel rollouts, but existing approaches are typically applied offline and do not adapt as environmental conditions change. We present Adaptive-MHE an online sampling-based Sys-ID framework, based on moving horizon estimation (MHE), that estimates the physical parameters of objects and terrain in the environment (e.g., mass, friction) and couples this estimate with a sampling-based model predictive controller, enabling adaptive loco-manipulation in changing and uncertain environments. In simulation and hardware experiments, our framework consistently outperforms baselines and matches the performance of a controller with access to ground-truth parameters.
Abstract:Legged robots have demonstrated a remarkable ability to traverse various terrains, yet generating effective loco-manipulation behaviors remains challenging. A key difficulty is that object and terrain parameters are typically unknown to the robot, and mismatches between these parameters and their simulated counterparts introduce a sim-to-real gap that degrades control performance. Classical system identification (Sys-ID) methods often assume differentiable dynamics, an assumption that does not hold for contact-rich legged systems. Sampling-based Sys-ID avoids this restriction by directly matching simulated and recorded state trajectories through massively parallel rollouts, but existing approaches are typically applied offline and do not adapt as environmental conditions change. We present Adaptive-MHE an online sampling-based Sys-ID framework, based on moving horizon estimation (MHE), that estimates the physical parameters of objects and terrain in the environment (e.g., mass, friction) and couples this estimate with a sampling-based model predictive controller, enabling adaptive loco-manipulation in changing and uncertain environments. In simulation and hardware experiments, our framework consistently outperforms baselines and matches the performance of a controller with access to ground-truth parameters.
Robotics (cs.RO)
arXiv:2609.17832 [cs.RO]
(or arXiv:2609.17832v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2609.17832 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 263 words
Related coverage
Learning Terrain-Aware Whole-Body Control for Perceptive Legged Loco-Manipulation
arXiv · Sep 4, 2026
Build a Physical AI model factory with NVIDIA Cosmos 3 on SageMaker HyperPod
AWS · Sep 4, 2026
Dyna-2: General Purpose Physical Agents with Hour-Long Autonomy — Jason Ma, Dyna Robotics
Latent Space · Oct 13, 2026
[AINews] not much happened today
Latent Space · Sep 10, 2026