| Differentiable Physics Models for Real-world Offline Model-based Reinforcement Learning M Lutter, J Silberbauer, J Watson, J Peters International Conference on Robotics and Automation, 2020 | 56 | 2020 |
| Real-world, Real-time Robotic Grasping with Convolutional Neural Networks J Watson, J Hughes, F Iida Annual Conference Towards Autonomous Robotic Systems, 2017 | 45 | 2017 |
| Stochastic Optimal Control as Approximate Input Inference J Watson, H Abdulsamad, J Peters Conference on Robot Learning, 2020 | 39 | 2020 |
| Benchmarking Structured Policies and Policy Optimization for Real-world Dexterous Object Manipulation N Funk, C Schaff, R Madan, T Yoneda, JU De Jesus, J Watson, ... IEEE Robotics and Automation Letters, 2021 | 37 | 2021 |
| Latent Derivative Bayesian Last Layer Networks J Watson*, JA Lin*, P Klink, J Pajarinen, J Peters International Conference on Artificial Intelligence and Statistics, 2021 | 34 | 2021 |
| Control as Inference? Comparing Path Integral and Message Passing Methods for Optimal Control J Watson Reinforcement Learning Algorithms: Analysis and Applications, 2021 | 32* | 2021 |
| Active Inference or Control as Inference? A Unifying View J Watson, A Imohiosen, J Peters International Workshop on Active Inference, 2020 | 19* | 2020 |
| Real Robot Challenge: A Robotics Competition in the Cloud S Bauer, M Wüthrich, F Widmaier, A Buchholz, S Stark, A Goyal, ... NeurIPS 2021 Competitions and Demonstrations Track, 2022 | 18* | 2022 |
| A Differentiable Newton Euler Algorithm for Multi-body Model Learning M Lutter, J Silberbauer, J Watson, J Peters ICML Workshop on Inductive Biases, Invariances and Generalization in RL, 2020 | 14 | 2020 |
| Coherent Soft Imitation Learning J Watson, SH Huang, N Heess Advances in Neural Information Processing Systems, 2023 | 11 | 2023 |
| Inferring Smooth Control: Monte Carlo Posterior Policy Iteration with Gaussian Processes J Watson, J Peters Conference on Robot Learning, 2022 | 11 | 2022 |
| Efficient Stochastic Optimal Control through Approximate Bayesian Input Inference J Watson, H Abdulsamad, R Findeisen, J Peters arXiv e-prints, arXiv: 2105.07693, 2021 | 11* | 2021 |
| Neural Linear Models with Functional Gaussian Process Priors J Watson*, JA Lin*, P Klink, J Peters Advances in Approximate Bayesian Inference, 2021 | 10 | 2021 |
| Advancing Trajectory Optimization with Approximate Inference: Exploration, Covariance Control and Adaptive Risk J Watson, J Peters American Control Conference, 2021 | 9 | 2021 |
| A Differentiable Newton–Euler Algorithm for Real-World Robotics M Lutter, J Silberbauer, J Watson, J Peters Inductive Biases in Machine Learning for Robotics and Control, 2023 | 7 | 2023 |
| Machine Learning with Physics Knowledge for Prediction: A Survey J Watson, C Song, O Weeger, T Gruner, AT Le, K Hansel, A Hendawy, ... arXiv preprint arXiv:2408.09840, 2024 | 3 | 2024 |
| Global Tensor Motion Planning AT Le, K Hansel, J Carvalho, J Watson, J Urain, A Biess, G Chalvatzaki, ... arXiv preprint arXiv:2411.19393, 2024 | | 2024 |
Jan PetersProfessor for Intelligent Autonomous Systems/TU Darmstadt, Dept. Head/German AI Research Center DFKIVerified email at ias.tu-darmstadt.de