Marc Toussaint

98 publications

22 venues

H Index 24


TU Berlin, Germany
University of Edinburgh, UK


Name Venue Year citations
Prediction of Human Full-Body Movements with Motion Optimization and Recurrent Neural Networks. ICRA 2020 0
Deep Visual Heuristics: Learning Feasibility of Mixed-Integer Programs for Manipulation Planning. ICRA 2020 0
A Probabilistic Framework for Constrained Manipulations and Task and Motion Planning under Uncertainty. ICRA 2020 0
Motion Planning Explorer: Visualizing Local Minima Using a Local-Minima Tree. IEEE Robotics and Automation Letters 2020 0
Describing Physics For Physical Reasoning: Force-Based Sequential Manipulation Planning. IEEE Robotics and Automation Letters 2020 0
Trajectory-Based Off-Policy Deep Reinforcement Learning. ICML 2019 0
Combined Task and Motion Planning under Partial Observability: An Optimization-Based Approach. ICRA 2019 2
Active Multi-Contact Continuous Tactile Exploration with Gaussian Process Differential Entropy. ICRA 2019 0
Planning Approximate Exploration Trajectories for Model-Free Reinforcement Learning in Contact-Rich Manipulation. IEEE Robotics and Automation Letters 2019 0
Differentiable Physics and Stable Modes for Tool-Use and Manipulation Planning - Extended Abtract. IJCAI 2019 0
An Optimal Algorithm to Solve the Combined Task Allocation and Path Finding Problem. IROS 2019 0
Active Inverse Model Learning with Error and Reachable Set Estimates. IROS 2019 0
Planning Ergonomic Sequences of Actions in Human-Robot Interaction. ICRA 2018 2
Bayesian Functional Optimization. AAAI 2018 0
Kinematic Morphing Networks for Manipulation Skill Transfer. IROS 2018 1
Differentiable Physics and Stable Modes for Tool-Use and Manipulation Planning. RSS 2018 24
Learning manipulation skills from a single demonstration. IJRR 2018 6
Probabilistic Recurrent State-Space Models. ICML 2018 13
Towards Combining Motion Optimization and Data Driven Dynamical Models for Human Motion Prediction. Humanoids 2018 3
Learning to Control Redundant Musculoskeletal Systems with Neural Networks and SQP: Exploiting Muscle Properties. ICRA 2018 2
Efficient behavior learning in human-robot collaboration. Autonomous Robots 2018 0
Constrained Bayesian optimization of combined interaction force/task space controllers for manipulations. ICRA 2017 7
Preference learning on the execution of collaborative human-robot tasks. ICRA 2017 4
Physical problem solving: Joint planning with symbolic, geometric, and dynamic constraints. Cognitive Science 2017 12
Optimizing Long-term Predictions for Model-based Policy Search. CoRL 2017 12
Opening a lockbox through physical exploration. Humanoids 2017 3
Inverse KKT: Learning cost functions of manipulation tasks from demonstrations. IJRR 2017 0
Active learning with query paths for tactile object shape exploration. IROS 2017 6
Multi-bound tree search for logic-geometric programming in cooperative manipulation domains. ICRA 2017 11
Policy Search in Reproducing Kernel Hilbert Space. IJCAI 2016 12
Relational activity processes for modeling concurrent cooperation. ICRA 2016 15
Combined Optimization and Reinforcement Learning for Manipulation Skills. RSS 2016 14
Fast greedy insertion and deletion in sparse Gaussian process regression. ESANN 2015 1
Robot programming from demonstration, feedback and transfer. IROS 2015 16
Sparse Gaussian process regression for compliant, real-time robot control. ICRA 2015 5
Probabilistic Inference Techniques for Scalable Multiagent Decision Making. JAIR 2015 19
Safe Exploration for Active Learning with Gaussian Processes. ECML/PKDD 2015 32
Hierarchical Monte-Carlo Planning. AAAI 2015 21
Understanding the geometry of workspace obstacles in Motion Optimization. ICRA 2015 22
An Approximate Inference Approach to Temporal Optimization for Robotics. ISRR 2015 2
Inverse KKT - Learning Cost Functions of Manipulation Tasks from Demonstrations. ISRR 2015 23
Touch based POMDP manipulation via sequential submodular optimization. Humanoids 2015 7
Temporal segmentation of pair-wise interaction phases in sequential manipulation demonstrations. IROS 2015 10
Discovering temporally extended features for reinforcement learning in domains with delayed causalities. ESANN 2015 1
Active exploration of joint dependency structures. ICRA 2015 12
POMDP manipulation via trajectory optimization. IROS 2015 9
Logic-Geometric Programming: An Optimization-Based Approach to Combined Task and Motion Planning. IJCAI 2015 55
Direct Loss Minimization Inverse Optimal Control. RSS 2015 20
Automatic testing and minimax optimization of system parameters for best worst-case performance. IROS 2015 3
Model-Based Relational RL When Object Existence is Partially Observable. ICML 2014 4
Dual execution of optimized contact interaction trajectories. IROS 2014 11
Entropy-based strategies for physical exploration of the environment's degrees of freedom. IROS 2014 16
Discovering relevant task spaces using inverse feedback control. Autonomous Robots 2014 3
Reactive phase and task space adaptation for robust motion execution. IROS 2014 8
Caging complex objects with geodesic balls. IROS 2013 9
Topology-based representations for motion planning and generalization in dynamic environments with interactions. IJRR 2013 22
On Stochastic Optimal Control and Reinforcement Learning by Approximate Inference (Extended Abstract). IJCAI 2013 3
Optimizing motion primitives to make symbolic models more predictive. ICRA 2013 4
Uncertainty aware grasping and tactile exploration. ICRA 2013 36
Active Learning for Teaching a Robot Grounded Relational Symbols. IJCAI 2013 53
Fast motion planning from experience: trajectory prediction for speeding up movement generation. Autonomous Robots 2013 43
Path Integral Control by Reproducing Kernel Hilbert Space Embedding. IJCAI 2013 0
Message-Passing Algorithms for MAP Estimation Using DC Programming. AISTATS 2012 5
On Stochastic Optimal Control and Reinforcement Learning by Approximate Inference. RSS 2012 0
Exploration in Model-based Reinforcement Learning by Empirically Estimating Learning Progress. NIPS/NeurIPS 2012 65
Hierarchical Motion Planning in Topological Representations. RSS 2012 1
Exploration in relational domains for model-based reinforcement learning. JMLR 2012 35
Analyzing and Escaping Local Optima in Planning as Inference for Partially Observable Domains. ECML/PKDD 2011 8
Scalable Multiagent Planning Using Probabilistic Inference. IJCAI 2011 39
Task Space Retrieval Using Inverse Feedback Control. ICML 2011 21
Escaping local optima in POMDP planning as inference. AAMAS 2011 2
Gaussian process implicit surfaces for shape estimation and grasping. ICRA 2011 92
Planning with Noisy Probabilistic Relational Rules. JAIR 2010 70
An Approximate Inference Approach to Temporal Optimization in Optimal Control. NIPS/NeurIPS 2010 26
Trajectory prediction in cluttered voxel environments. ICRA 2010 22
Probabilistic Backward and Forward Reasoning in Stochastic Relational Worlds. ICML 2010 3
Integrated motor control, planning, grasping and high-level reasoning in a blocks world using probabilistic inference. ICRA 2010 40
Exploration in Relational Worlds. ECML/PKDD 2010 16
Trajectory prediction: learning to map situations to robot trajectories. ICML 2009 38
Model-free reinforcement learning as mixture learning. ICML 2009 35
Approximate inference for planning in stochastic relational worlds. ICML 2009 21
Multi-class image segmentation using conditional random fields and global classification. ICML 2009 62
Robot trajectory optimization using approximate inference. ICML 2009 168
Relevance Grounding for Planning in Relational Domains. ECML/PKDD 2009 17
Learning model-free robot control by a Monte Carlo EM algorithm. Autonomous Robots 2009 51
Hierarchical POMDP Controller Optimization by Likelihood Maximization. UAI 2008 69
Task maps in humanoid robot manipulation. IROS 2008 36
Optimization of fluent approach and grasp motions. Humanoids 2008 23
A Primitive Based Generative Model to Infer Timing Information in Unpartitioned Handwriting Data. IJCAI 2007 11
Modelling motion primitives and their timing in biologically executed movements. NIPS/NeurIPS 2007 36
Optimization of sequential attractor-based movement for compact behaviour generation. Humanoids 2007 50
Probabilistic inference for structured planning in robotics. IROS 2007 26
Probabilistic inference for solving discrete and continuous state Markov Decision Processes. ICML 2006 134
Learning Multiple Models of Non-linear Dynamics for Control Under Varying Contexts. ICANN 2006 15
Extracting Motion Primitives from Natural Handwriting Data. ICANN 2006 34
Learning discontinuities with products-of-sigmoids for switching between local models. ICML 2005 19
Learning discontinuities for switching between local models. IJCAI 2005 6
Learning a World Model and Planning with a Self-Organizing, Dynamic Neural System. NIPS/NeurIPS 2003 22
Copyright ©2019 Universität Würzburg

Impressum | Privacy | FAQ