Planning Reactive Manipulation in Dynamic Environments

  title={Planning Reactive Manipulation in Dynamic Environments},
  author={Philipp S. Schmitt and Florian Wirnshofer and Kai M. Wurm and Georg von Wichert and Wolfram Burgard},
  journal={2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
When robots perform manipulation tasks, they need to determine their own movement, as well as how to make and break contact with objects in their environment. Reasoning about the motions of robots and objects simultaneously leads to a constrained planning problem in a high-dimensional state-space. Additionally, when environments change dynamically motions must be computed in real-time.To this end, we propose a feedback planner for manipulation. We model manipulation as constrained motion and… 

Figures and Tables from this paper

Dynamic Grasping with Reachability and Motion Awareness

A dynamic grasping framework that is reachability-aware and motion-aware, and a seeding approach for arm motion generation that utilizes solution from previous time step is presented.

Towards a Generic Manipulation Framework for Robots based on Model Predictive Interaction Control

An optimization-based control framework for robotic manipulation tasks based on the concept of model predictive interaction control (MPIC) and the generic control concept are demonstrated for a screwing application using a robot arm with seven degrees of freedom.

Domain Optimization for Hierarchical Planning based on Set-Theory

A domain optimization algorithm for hierarchical planners that uses a set-based formulation that reduces the effects of the non-optimality that comes with the hierarchical approach is presented.

A Stack-of-Tasks Approach Combined With Behavior Trees: A New Framework for Robot Control

This letter combines the SoT control strategy with Behavior Trees (BTs), a task switching structure that addresses some of the limitations of the FSMs in terms of reactivity, modularity and re-usability, and shows the robustness of the framework.

Efficient Object Manipulation to an Arbitrary Goal Pose: Learning-Based Anytime Prioritized Planning

A learning-driven anytime prioritized search-based solver to find a feasible solution with low path cost in a short time, and can achieve better performances in the object manipulation task with less time and less cost.

Survivable Hyper-Redundant Robotic Arm with Bayesian Policy Morphing

A Bayesian reinforcement learning framework that allows robotic manipulators to adaptively recover from random mechanical failures autonomously, hence being survivable, and it is shown that policy search, in the direction biased by prior experience, significantly improves learning efficiency in terms of sampling requirements.

GraspARL: Dynamic Grasping via Adversarial Reinforcement Learning

This work introduces an adversarial reinforcement learning framework for dynamic grasping, namely GraspARL, and formulate the dynamic grasping problem as a “move-andgrasp” game, where the robot is to pick up the object on the mover and the adversarial mover is to find a path to escape it.

Reactive Whole-Body Obstacle Avoidance for Collision-Free Human-Robot Interaction with Topological Manifold Learning

A novel methodology of reactive whole-body obstacle avoidance methodology that safeguards the human who enters the robot’s workspace through achieving conflict-free human-robot interactions even in a dynamically constrained environment is presented.

A Differentiable Recipe for Learning Visual Dexterous Planar Manipulation

  • Computer Science
  • 2021
This work proposes a novel learning architecture that combines video decoding neural models with priors from contact mechanics by leveraging differentiable optimization and differentiable simulation and finds that its modular and fully differentiable architecture outperforms learning-only methods on unseen objects and motions.

Learning adaptive control in dynamic environments using reproducing kernel priors with bayesian policy gradients

This paper proposes to use vector-valued kernel embedding (instead of parameter vectors) to represent policy distribution as features in non-decreasing Euclidean space, and develops policy search algorithm over Bayesian posterior estimation derived from inner-product of a priori Gaussian kernels.



Optimal, sampling-based manipulation planning

This paper proposes an asymptotically optimal manipulation planner that extends optimal sampling-based roadmap planners to efficiently explore the configuration space of the robot and the object and proves probabilistic completeness and global, asymPTotic optimality.

Modeling and Planning Manipulation in Dynamic Environments

A new model for sequential manipulation tasks that also considers robot dynamics and time-variant environments is proposed and automatically derive constraint-based controllers and use them as steering functions in a kinodynamic manipulation planner.

Sampling-Based Methods for Motion Planning with Constraints

This survey describes the families of methods for sampling-based planning with constraints and places them on a spectrum delineated by their complexity and focuses on the representation of constraints and sampling- based planners that incorporate constraints.

Extending the iTaSC Constraint-based Robot Task Specification Framework to Time-Independent Trajectories and User-Configurable Task Horizons

This paper extends a generic modeling approach for geometrically complex robot tasks to include task constraints that are not given as explicit functions of time, to allow task programmers to make a trade-off between computational speed and (global) task optimality.

A geometrical approach to planning manipulation tasks. The case of discrete placements and grasps

The problem is shown to be a constrained instance of the coordinated motion planning problem for multiple moving bodies, and the constraints are related to the placement and the motion of objects, and can be expressed geometrically.

Asymptotically Optimal Planning under Piecewise-Analytic Constraints

It is demonstrated that, given the ability to sample from the locally reachable subset of the configuration space with positive probability, the first asymptotically optimal algorithm for motion planning problems with piecewise-analytic differential constraints can construct random geometric graphs that contain optimal plans with probability one in the limit of infinite samples.

Task Planning with Continuous Actions and Nondeterministic Motion Planning Queries

It is proved that PTR is probabilistically complete under relatively weak conditions with a convergence rate that improves with the abundance of actions that admit easy motion planning queries, and scales well to high dimensional problems.

Sensor-Based Reactive Execution of Symbolic Rearrangement Plans by a Legged Mobile Manipulator

This work demonstrates the physical rearrangement of wheeled stools in a moderately cluttered indoor environment by a quadrupedal robot that autonomously achieves a user's desired configuration using a three layer hierarchical architecture.

Constraint-based Task Specification and Estimation for Sensor-Based Robot Systems in the Presence of Geometric Uncertainty

This paper introduces a systematic constraint-based approach to specify complex tasks of general sensor-based robot systems consisting of rigid links and joints. The approach integrates both

Sequential Composition of Dynamically Dexterous Robot Behaviors

Experimental results from an implementation of a sequential robot controller-composition technique in the context of dexterous “batting” maneuvers are reported, and descriptive statistics characterizing the experiments are presented.