Multi-Robot Collision Avoidance under Uncertainty with Probabilistic Safety Barrier Certificates

Authors: Wenhao Luo, Wen Sun, Ashish Kapoor

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate effectiveness of the approach through experiments on realistic simulation environments.
Researcher Affiliation Collaboration Wenhao Luo The Robotics Institute Carnegie Mellon University wenhaol@cs.cmu.edu Wen Sun Computer Science Department Cornell University ws455@cornell.edu Ashish Kapoor Microsoft Corporation Redmond, Washington 98033 akapoor@microsoft.com
Pseudocode No The paper does not contain any pseudocode or clearly labeled algorithm blocks.
Open Source Code Yes Code is available online at https://github.com/wenhaol/Pr SBC.
Open Datasets No The paper describes simulation experiments rather than using a traditional publicly available dataset with splits. While it mentions Air Sim as an open-source simulation environment, it does not provide access information for any generated or used 'datasets' for training/evaluation.
Dataset Splits No The paper describes simulation scenarios and parameters but does not specify training, validation, and test dataset splits in the conventional sense for reproducibility.
Hardware Specification Yes The simulations are on personal laptop with Intel Core i7-8750H CPU of 2.20 GHz.
Software Dependencies No The paper mentions 'Air Sim [21]' as an open-source simulation environment, but it does not specify any version numbers for Air Sim or other software dependencies, which is required for reproducible software descriptions.
Experiment Setup Yes The robot safety radius is set to be Ri = 0.2m and has bounded uniformly distributed localization error denoted by the red error box accounting for the safety radius. ... Maximum velocity limit is 0.1m/sec for the robots and robots motion is disturbed by randomly generated bounded noise with magnitude up to 0.07m/sec. The inter-robot collision-free confidence level σ set to be 0.9.