Interactive Learning
Learning Human-Aware Cooperation
Reference:
Simultaneously Learning Intentions and Preferences during Physical Human-Robot Cooperation. Autonomous Robots, 48(4):11, 2024. .Safe Interactive Movement Primitive Learning (SIMPLe)
Reference:
Interactive Imitation Learning of Bimanual Movement Primitives. IEEE/ASME Transactions on Mechatronics, :1–13, 2023. Early Access. .
Interactive Corrections and Reinforcements for an Epistemic and Aleatoric uncertainty-aware Teaching (ICREATe)
Reference:
Knowledge- and Ambiguity-Aware Robot Learning from Corrective and Evaluative Feedback. Neural Computing and Applications, 35(23):16821–16839, 2023. .
Combining Interactive Teaching and Self-Exploration
Reference:
Solving Robot Assembly Tasks by Combining Interactive Teaching and Self-Exploration. arXiv:2209.11530 [cs.RO], 2022. .
Social Model Predictive Contouring Control (Social-MPCC)
Reference:
Visually-Guided Motion Planning for Autonomous Driving from Interactive Demonstrations. Engineering Applications of Artificial Intelligence, 116:105277, 2022. .
Interactive Learning of Stiffness and Attractors (ILoSA)
Reference:
ILoSA: Interactive Learning of Stiffness and Attractors. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 7778–7785, 2021. .
Learning Interactively to Resolve Ambiguity (LIRA)
Reference:
Learning Interactively to Resolve Ambiguity in Reference Frame Selection. In 2020 Conference on Robot Learning (CoRL) (Jens Kober, Fabio Ramos, Claire Tomlin, eds.), PMLR, vol. 155 of Proceedings of Machine Learning Research, pp. 1298–1311, 2021. .
Teaching Imitative Policies in State-space (TIPS)
Reference:
Interactive Imitation Learning in State-Space. In 2020 Conference on Robot Learning (CoRL) (Jens Kober, Fabio Ramos, Claire Tomlin, eds.), PMLR, vol. 155 of Proceedings of Machine Learning Research, pp. 682–692, 2021. .
Interactive Learning of Temporal Features for Control
Reference:
Interactive Learning of Temporal Features for Control: Shaping Policies and State Representations From Human Feedback. IEEE Robotics & Automation Magazine, 27(2):46–54, 2020. .
Predictive Probabilistic Merging of Policies (PPMP)
Reference:
Deep Reinforcement Learning with Feedback-based Exploration. In IEEE Conference on Decision and Control (CDC), pp. 803–808, 2019. .
Gaussian Process Coach (GPC)
Reference:
Learning Gaussian Policies from Corrective Human Feedback. arXiv:1903.05216 [cs.LG], 2019. .
Enhanced Deep COACH (enhanced D-COACH)
Reference:
Continuous Control for High-Dimensional State Spaces: An Interactive Learning Approach. In IEEE International Conference on Robotics and Automation (ICRA), pp. 7611–7617, 2019. .
Deep COACH (D-COACH)
Reference:
Interactive Learning with Corrective Feedback for Policies based on Deep Neural Networks. In Proceedings of the 2018 International Symposium on Experimental Robotics (ISER 2018) (Jing Xiao, Torsten Kröger, Oussama Khatib, eds.), Springer International Publishing, pp. 353–363, 2020. .
Deep Reinforcement Learning
Fine-tuning Deep RL with Gradient-Free Optimization
Reference:
Fine-tuning Deep RL with Gradient-Free Optimization. In 21th IFAC World Congress, pp. 8049–8056, 2020. .
Experience Selection Baselines
Reference:
Experience Selection in Deep Reinforcement Learning for Control. Journal of Machine Learning Research, 19(9):1–56, 2018. .
Imitation Learning
Policy via neUral Metric leArning (PUMA)
Reference:
Gaussian Process Transportation (GPT)
ILeSiA: Interactive Learning of Situational Awareness from Camera Input. arXiv:2409.20173 [cs.RO], 2024. .CONvergent Dynamics from demOnstRations (CONDOR)
Reference:
Stable Motion Primitives via Imitation and Contrastive Learning. IEEE Transactions on Robotics, 39(5):3909–3928, 2023. .Learning Task-Parameterzied Skills from Few Demonstrations
Reference:
Learning Task-Parameterized Skills from Few Demonstrations. IEEE Robotics and Automation Letters, 7(2):4063–4070, 2022. The contents of this paper were also selected by ICRA'22 Program Committee for presentation at the Conference. .
Quadrupeds
Curriculum-Based Reinforcement Learning for Quadrupedal Jumping
Reference:
Curriculum-Based Reinforcement Learning for Quadrupedal Jumping: A Reference-free Design. IEEE Robotics & Automation Magazine, 2024. Accepted. .
Quadruped-Sim
Reference:
Two-Stage Learning of Highly Dynamic Motions with Rigid and Articulated Soft Quadrupeds. In IEEE International Conference on Robotics and Automation (ICRA), pp. 9720–9726, 2024. .
Others
Efficient Parallelized Simulation of Cyber-Physical Systems
Reference:
Efficient Parallelized Simulation of Cyber-Physical Systems. Transactions on Machine Learning Research, 2024. Reproducibility Certification. .Robust Multi-Modal Density Estimation (ROME)
Reference:
ROME: Robust Multi-Modal Density Estimation. In Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI) (Kate Larson, ed.), International Joint Conferences on Artificial Intelligence Organization, pp. 4751–4759, 2024. Main Track. .Evaluating the Commotions model
Reference:
Using Models Based on Cognitive Theory to Predict Human Behavior in Traffic: A Case Study. In IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), pp. 5870–5875, 2023. .Framework for Benchmarking Gap Acceptance
Reference:
Benchmarking Behavior Prediction Models in Gap Acceptance Scenarios. IEEE Transactions on Intelligent Vehicles, 8(3):2580–2591, 2023. .Disagreement-Aware Variable Impedance Control (DAVI)
Reference:
Disagreement-Aware Variable Impedance Control for Online Learning of Physical Human-Robot Cooperation Tasks. In ICRA 2022 full day workshop - Shared Autonomy in Physical Human-Robot Interaction: Adaptability and Trust, 2022. .
Random Shadows and Highlights
Reference:
Random Shadows and Highlights: A New Data Augmentation Method for Extreme Lighting Conditions. arXiv:2101.05361 [cs.CV], 2021. .
Policy learning by Weighting Exploration with the Returns (PoWER)
A basic MATLAB/Octave implementation of Policy learning by Weighting Exploration with the Returns (PoWER) [4 variants: return or state-action value function, constant exploration or automatic adaptation], episodic Reward-Weighted Regression (eRWR), episodic Natural Actor Critic (eNAC), ‘Vanilla’ Policy Gradients (VPG), and Finite Difference Gradients (FDG): matlab_PoWER.zip
The required motor primitive code can be downloaded from http://www-clmc.usc.edu/Resources/Software backup April 26, 2020
Reference:
Policy Search for Motor Primitives in Robotics. Machine Learning, 84(1-2):171–203, 2011. .
DMPs for hitting and batting
A basic MATLAB/Octave implementation: hittingMP.m
Reference:
Movement Templates for Learning of Hitting and Batting. In IEEE International Conference on Robotics and Automation (ICRA), pp. 69–82, 2010. .