A Transferable Legged Mobile Manipulation Framework Based on Disturbance Predictive Control

  title={A Transferable Legged Mobile Manipulation Framework Based on Disturbance Predictive Control},
  author={Qingfeng Yao and Jilong Wang and Shuyu Yang and Cong Wang and Linghan Meng and Qifeng Zhang and Donglin Wang},
Due to their ability to adapt to different terrains, quadruped robots have drawn much attention in the research field of robot learning. Legged mobile manipulation, where a quadruped robot is equipped with a robotic arm, can greatly enhance the performance of the robot in diverse manipulation tasks. Several prior works have investigated legged mobile manipulation from the viewpoint of control theory. However, modeling a unified structure for various robotic arms and quadruped robots is a… 

Figures and Tables from this paper



Generating Continuous Motion and Force Plans in Real-Time for Legged Mobile Manipulation

This paper presents the Stability and Task Oriented Receding-Horizon Motion and Manipulation Autonomous Planner (STORMMAP) that is able to generate continuous plans for the robot’s motion and manipulation force trajectories that ensure dynamic feasibility and stability of the platform, and incentivizes accomplishing manipulation and motion tasks specified by a user.

Learning a State Representation and Navigation in Cluttered and Dynamic Environments

A learning-based pipeline to realise local navigation with a quadrupedal robot in cluttered environments with static and dynamic obstacles is presented, which is trained to not only estimate the hidden state of the world in an unsupervised fashion, but also helps bridging the reality gap, enabling successful sim-to-real transfer.

A Unified MPC Framework for Whole-Body Dynamic Locomotion and Manipulation

A whole-body planning framework that unifies dynamic locomotion and manipulation tasks by formulating a single multi-contact optimal control problem and introduces a set of constraints that can encode any pre-defined gait sequence or manipulation schedule in the formulation.

Deep Latent Competition: Learning to Race Using Visual Control Policies in Latent Space

Deep Latent Competition is presented, a novel reinforcement learning algorithm that learns competitive visual control policies through self-play in imagination that reduces costly sample generation in the real world, while the latent representation enables planning to scale gracefully with observation dimensionality.

Robust Autonomous Navigation of a Small-Scale Quadruped Robot in Real-World Environments

This paper proposes a system integration of a small-scale quadruped robot, the MIT Mini-Cheetah Vision, that exteroceptively senses the terrain and dynamically explores the world around it at high velocities and devise a hierarchical state estimator that integrates kinematic, IMU, and localization sensor data to provide state estimates specific to path planning and locomotion tasks.

Multi-expert learning of adaptive legged locomotion

This work demonstrated successful multiskill locomotion on a real quadruped robot that performed coherent trotting, steering, and fall recovery autonomously and showed the merit of multi-expert learning generating behaviors that can adapt to unseen scenarios.

RLOC: Terrain-Aware Legged Locomotion using Reinforcement Learning and Optimal Control

A unified model-based and data-driven approach for quadrupedal planning and control to achieve dynamic locomotion over uneven terrain using on-board proprioceptive and exteroceptive feedback and a reinforcement learning policy trained over a wide range of procedurally generated terrains.

From Pixels to Legs: Hierarchical Learning of Quadruped Locomotion

It is shown that hierarchical policies can concurrently learn to locomote and navigate in these environments, and show they are more efficient than non-hierarchical neural network policies.

Robust Quadruped Jumping via Deep Reinforcement Learning

This paper proposes a framework using deep reinforcement learning to leverage the complex solution of nonlinear trajectory optimization for quadrupedal jumping to improve the robustness to allow jumping off of significantly uneven terrain with variable robot dynamical parameters.

Learning Latent Representations to Influence Multi-Agent Interaction

This work proposes a reinforcement learning-based framework for learning latent representations of an agent's policy, where the ego agent identifies the relationship between its behavior and the other agent's future strategy and leverages these latent dynamics to influence the otherAgent, purposely guiding them towards policies suitable for co-adaptation.