Perceptive Model Predictive Control for Continuous Mobile Manipulation

Pankert, Johannes; Hutter, Marco

doi:10.1109/lra.2020.3010721

Cited by 66 publications

(55 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ashe and Krishna (2020) used MPC for dynamic target tracking and obstacle avoidance for a personfollowing robot. Pankert and Hutter (2020) used MPC for continuous mobile manipulation and collision avoidance. Other researchers used MPC for controlling an autonomous vehicle and performing obstacle avoidance (Quirynen et al, 2020;Song and Huh, 2021).…”

Section: Related Workmentioning

confidence: 99%

Kinematic-Model-Free Predictive Control for Robotic Manipulator Target Reaching With Obstacle Avoidance

Chappell

Kormushev

2022

Front. Robot. AI

View full text Add to dashboard Cite

Model predictive control is a widely used optimal control method for robot path planning and obstacle avoidance. This control method, however, requires a system model to optimize control over a finite time horizon and possible trajectories. Certain types of robots, such as soft robots, continuum robots, and transforming robots, can be challenging to model, especially in unstructured or unknown environments. Kinematic-model-free control can overcome these challenges by learning local linear models online. This paper presents a novel perception-based robot motion controller, the kinematic-model-free predictive controller, that is capable of controlling robot manipulators without any prior knowledge of the robot’s kinematic structure and dynamic parameters and is able to perform end-effector obstacle avoidance. Simulations and physical experiments were conducted to demonstrate the ability and adaptability of the controller to perform simultaneous target reaching and obstacle avoidance.

show abstract

Section: Related Workmentioning

confidence: 99%

Kinematic-Model-Free Predictive Control for Robotic Manipulator Target Reaching With Obstacle Avoidance

Chappell

Kormushev

2022

Front. Robot. AI

View full text Add to dashboard Cite

show abstract

“…The recent work in [19] shows collision-free planning of end-effector trajectories of a mobile manipulator. The authors add soft inequality constraints with relaxed barrier functions to the MPC cost, and a set of collision spheres to approximate the robot.…”

Section: A Related Workmentioning

confidence: 99%

“…Upon receiving a new map, we pre-compute the gradient for each voxel of the distance-field and cache it alongside its distance to make the queries within the MPC optimization faster. This caching functionality is taken from [19], although we clip the norm of this gradient to be within its theoretical limits [0, 1] to compensate for errors introduced by finite-difference approximation and the voxelization of the distance field 3 . As the computation time of the distance field update is cubic in the voxel size, we need to trade-off between update rate and resolution.…”

Section: B Environment Representationmentioning

confidence: 99%

Collision-Free MPC for Legged Robots in Static and Dynamic Scenes

Gaertner

Bjelonic

Farshidian

et al. 2021

2021 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

We present a model predictive controller (MPC) that automatically discovers collision-free locomotion while simultaneously taking into account the system dynamics, friction constraints, and kinematic limitations. A relaxed barrier function is added to the optimization's cost function, leading to collision avoidance behavior without increasing the problem's computational complexity. Our holistic approach does not require any heuristics and enables legged robots to find wholebody motions in the presence of static and dynamic obstacles. We use a dynamically generated euclidean signed distance field for static collision checking. Collision checking for dynamic obstacles is modeled with moving cylinders, increasing the responsiveness to fast-moving agents. Furthermore, we include a Kalman filter motion prediction for moving obstacles into our receding horizon planning, enabling the robot to anticipate possible future collisions. Our experiments 1 demonstrate collision-free motions on a quadrupedal robot in challenging indoor environments. The robot handles complex scenes like overhanging obstacles and dynamic agents by exploring motions at the robot's dynamic and kinematic limits.

show abstract

“…Autonomous Mobile Manipulation: Algorithms for autonomous MM have been studied for decades [36,37], and have primarily been addressed with either control [38,39,40,41] or Task and motion planning (TaMP) [3,42,43,44] approaches. Both are are able to generalize across different robots, environments, and robots, but control approaches are generally limited to short horizon tasks, and TaMP approaches depend on human specification of the symbolic actions and full information about the 3D structure of the environment.…”

Section: Related Workmentioning

confidence: 99%

Error-Aware Imitation Learning from Teleoperation Data for Mobile Manipulation

Wong¹,

Tung²,

Kurenkov³

et al. 2021

Preprint

View full text Add to dashboard Cite

In mobile manipulation (MM), robots can both navigate within and interact with their environment and are thus able to complete many more tasks than robots only capable of navigation or manipulation. In this work, we explore how to apply imitation learning (IL) to learn continuous visuo-motor policies for MM tasks. Much prior work has shown that IL can train visuo-motor policies for either manipulation or navigation domains, but few works have applied IL to the MM domain. Doing this is challenging for two reasons: on the data side, current interfaces make collecting high-quality human demonstrations difficult, and on the learning side, policies trained on limited data can suffer from covariate shift when deployed. To address these problems, we first propose MOBILE MANIPULATION ROBOTURK (MOMART), a novel teleoperation framework allowing simultaneous navigation and manipulation of mobile manipulators, and collect a first-of-its-kind large scale dataset in a realistic simulated kitchen setting. We then propose a learned error detection system to address covariate shift by detecting when an agent is in a potential failure state. We train performant IL policies and error detectors from this data, and achieve over 45% task success rate and 85% error detection success rate across multiple multi-stage tasks when trained on expert data. Codebase, datasets, visualization, and more available at https://sites.google.com/view/il-for-mm/home.

show abstract

Perceptive Model Predictive Control for Continuous Mobile Manipulation

Cited by 66 publications

References 21 publications

Kinematic-Model-Free Predictive Control for Robotic Manipulator Target Reaching With Obstacle Avoidance

Kinematic-Model-Free Predictive Control for Robotic Manipulator Target Reaching With Obstacle Avoidance

Collision-Free MPC for Legged Robots in Static and Dynamic Scenes

Error-Aware Imitation Learning from Teleoperation Data for Mobile Manipulation

Contact Info

Product

Resources

About