Autonomous flipper control with safety constraints

Pecka, Martin; Šalanský, Vojtěch; Zimmermann, Karel; Svoboda, Tomáš

doi:10.1109/iros.2016.7759447

Cited by 21 publications

(15 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The detailed results are shown in Table I. A summary extracted from the test results is given in Table II. It is evident from the table that the track plate models are slower by an order of magnitude or two than the other models, which might become a problem when there is need to execute many rollouts in the simulator (in [15], each learning episode took about 1 hour with csm; with plates, it would take several days). We have also observed, that the 10 cm plates are too rough approximation of the smoothly curved belt, and the resulting model's motion could be described as "bumpy".…”

Section: Test Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Fast simulation of vehicles with non-deformable tracks

Pecka

Zimmermann

Svoboda

2017

2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

This paper presents a novel technique that allows for both computationally fast and sufficiently plausible simulation of vehicles with non-deformable tracks. The method is based on an effect we have called Contact Surface Motion. A comparison with several other methoddds for simulation of tracked vehicle dynamics is presented with the aim to evaluate methods that are available off-the-shelf or with minimum effort in general-purpose robotics simulators. The proposed method is implemented as a plugin for the open-source physics-based simulator Gazebo using the Open Dynamics Engine.

show abstract

Section: Test Resultsmentioning

confidence: 99%

“…If the real track has grousers, one way to add a similar effect to the simulation is to increase the friction coefficient. Despite it only looks like a workaround, this method proved useful in our previous work [15] where we heavily utilized the simulator to find a control policy suitable also for the real robot.…”

Section: Utilizing Contact Surface Motionmentioning

confidence: 99%

Fast simulation of vehicles with non-deformable tracks

Pecka

Zimmermann

Svoboda

2017

2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The main shortcoming of this work is the high processing cost induced from the employed CNN and slow convergence to the optimal policy. One of the most elaborate approaches for flipper control in the scenario of palette traversal is proposed by [16]. The main contribution concerns the use of contextual relative entropy policy search [17] by introducing safety constraints into the optimization problem.…”

Section: B Learning-based Approachesmentioning

confidence: 99%

“…For example, safety of actions could be estimated and a robot could be programmed to avoid such unsafe actions [13]. Another method is to incorporate a safety criterion inside a RL algorithm [16]. However, this does not generalize well across all RL algorithms.…”

Section: Safety Assessmentmentioning

confidence: 99%

Staircase Traversal via Reinforcement Learning for Active Reconfiguration of Assistive Robots

Mitriakov

Papadakis

Nguyen

et al. 2020

2020 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

View full text Add to dashboard Cite

Assistive robots introduce a new paradigm for developing advanced personalized services. At the same time, the variability and stochasticity of environments, hardware and unknown parameters of the interaction complicates their modelling, as in the case of staircase traversal. For this task, we propose to treat the problem of robot configuration control within a reinforcement learning framework, using policy gradient optimization. In particular, we examine the use of safety or traction measures as a means for endowing the learned policy with desired properties. Using the proposed framework, we present extensive qualitative and quantitative results where a simulated robot learns to negotiate staircases of variable size, while being subjected to different levels of sensing noise.

show abstract

“…[14] utilize reinforcement learning (RL) to accommodate the morphology to the terrain. Sequentially, [15] further enhance the capability of control with Relative Entropy Policy Search. Make effort on the observation, [6] model the incomplete measurement and make control on the robot morphology under RL.…”

Section: Introductionmentioning

confidence: 99%

Configuration-Space Flipper Planning for Rescue Robots

Yuan

Wang

Schwertfeger

2019

2019 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)

View full text Add to dashboard Cite

For rescue robots, flipper endows the robot with additional ability to pass through various terrain. Autonomous motion becomes more important. In recent work autonomy is done by either planning with several special states or based on collected data. We are considering if it is possible to find a way to build continues states without collecting old trail data. In this paper, we first model the possible states as a global planning path with parameter configuration of the scene. Then, we follows the path to achieve the autonomous run. We plot the morphology of each path points to show the correctness of the path and implement a simple path following on real robot to demonstrate the performance of our algorithm.

show abstract

Autonomous flipper control with safety constraints

Cited by 21 publications

References 13 publications

Fast simulation of vehicles with non-deformable tracks

Fast simulation of vehicles with non-deformable tracks

Staircase Traversal via Reinforcement Learning for Active Reconfiguration of Assistive Robots

Configuration-Space Flipper Planning for Rescue Robots

Contact Info

Product

Resources

About