Code

Benchmark Human-to-Robot Handovers of Unseen Containers with Unknown Filling
Baseline for a human-to-robot handovers of an unseen containers.
[code] [details]
Safe Handovers Towards safe human-to-robot handovers of unknown containers
Software of the real-to-simulation framework to conduct safe human-to-robot handovers with visual estimations of the physical properties of unknown cups or drinking glasses and of the human hands from videos of a person manipulating the object.
[code] [details]
LoDE LoDE: Localisation and Object Dimensions Estimator
Software of the method that jointly localises container-like objects and estimates their dimensions with a generative 3D sampling model and a multi-view 3D-2D iterative shape fitting, using two wide-baseline, calibrated RGB cameras.
[code] [details]
Benchmark WHC: Whole-Body Control with QP
Generic whole body control library with QP: inverse dynamics and kinematics.
[code]
Carefulness detection Carefulness detection
Dynamical Systems that can classify new, unknown handovers, as Careful Objects (comparable to handling a cup full of water) or Not-Careful Objects (comparable to handling an empty cup).
[code]
ACC ACC: Audio Content Classification
Software of the method that identifies the action performed by a person manipulating a food box or drinking glass (shaking or pouring) and then jointly classifies the content type and level witihin the container, using audio data converted into spectrograms.
[code] [details]
Neural Anisotropy Directions NADs: Neural Anisotropy Directions
Software that reproduces the results of Neural Anisotropy Directions: A sequence of vectors that encapsulate the directional inductive bias of an architecture and encode its preference to separate the input data based on some particular features.
[code] [paper] [details]
Hold Me Tight Hold me tight!
Software that reproduce the results and influence of discriminative features on deep network boundaries.
[code] [paper]
ColorFool ColorFool: Semantic Adversarial Colorization
Software that identifies image regions using a semantic segmentation model and generates adversarial images via perturbing color of semantic regions in the natural color range.
[code] [paper] [details]
Challenge Evaluation Toolkit
Official evaluation toolkit for the CORSMAL Challenge.
[code] [details]

Software from people using project data and models

Squids
Squids
Improving Generalization of Deep Networks for Estimating Physical Properties of Containers and Fillings
Software of the solution submitted by the team Squids at the 2022 ICASSP CORSMAL challenge.
[code] [paper]
KEIO-ICS Shared Transformer Encoder with Mask-based 3D Model Estimation for Container Mass Estimation
Software of the solution submitted by the team KEIO-ICS at the 2022 ICASSP CORSMAL challenge.
[code]
Visual Container localisation and mass estimation with an RGB-D camera
Software of the solution submitted by the team Visual at the 2022 ICASSP CORSMAL challenge.
[code] [paper]
Because It's Tactile Filling mass estimation using multi-modal observations of human-robot handovers
Software of the solution submitted by the Because It's Tactile team at the 2020 CORSMAL challenge.
[code] [paper] [video] [slides]
HVLR Audio-Visual Hybrid Approach for Filling Mass Estimation
Software of the solution submitted by the HVRL team at the 2020 CORSMAL challenge.
[code] [paper] [video] [slides]
NTNU-ERC NTNU-ERC solution for filling mass estimation
Software of the solution submitted by the NTNU-ERC team at the 2020 CORSMAL challenge.
[code] [slides]

Other software from the CORSMAL team and related to the project

A unified framework for coordinated multi-arm motion planning
S. S. Mirrazavi Salehian, N. Figueroa, A. Billard
The International Journal of Robotics Research, Vol. 37, Issue 10, pp. 1205-1232, April 2018.
Libraries for a unified framework designed to perform a coordinated multi-arm motion planning: a centralised inverse kinematics solver under self-collision avoidance.
[code] [paper]
A human-inspired controller for fluid human-robot handovers
J. Medina, F. Duvallet, M. Karnam, A. Billard
Proc. of Int. Conference on Humanoid Robots, Cancun, Mexico, 15-17 November 2016.
ROS package for estimating the load share of an object while being supported by a robot and a third party (such as a person).
[code] [paper]
Kuka-lwr-ros
ROS package to control the KUKA LWR 4 (both simulation and physical robot).
[code]
A long short-term memory convolutional neural network for first-person vision activity recognition
G. Abebe, A. Cavallaro
Proc. of ICCV workshop on Assistive Computer Vision and Robotics (ACVR), Venice, October 28, 2017.
Software for first person vision activities.
[code] [paper]
Inertial-Vision: cross-domain knowledge transfer for wearable sensors
G. Abebe, A. Cavallaro
Proc. of ICCV workshop on Assistive Computer Vision and Robotics (ACVR), Venice, October 28, 2017.
Software for classifying the activities from first-person videos using cross-domain knowledge transfer for wearable sensors.
[code] [paper]
Active visual tracking in multi-agent scenarios
Y. Wang, A. Cavallaro
Proc. of IEEE Int. Conference on Advanced Signal and Video based Surveillance (AVSS), Lecce, 29 August - 1 September, 2017.
Software for active visual target tracking in multi-agent scenarios.
[code] [paper]