Marc Toussaint

Marc Toussaint
Technische Universität Berlin | TUB · Department of Intelligent Systems

Dr. rer. nat.

About

256
Publications
29,597
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
5,330
Citations
Additional affiliations
March 2020 - present
Technische Universität Berlin
Position
  • Professor (Full)
December 2012 - February 2020
Universität Stuttgart
Position
  • Professor (Full)
October 2010 - November 2012
Freie Universität Berlin
Position
  • Group Leader

Publications

Publications (256)
Article
Full-text available
Although collective robotic construction systems are beginning to showcase how multi‐robot systems can contribute to building construction by efficiently building low‐cost, sustainable structures, the majority of research utilizes non‐structural or highly customized materials. A modular collective robotic construction system based on a robotic actu...
Preprint
It is a long-standing problem to find effective representations for training reinforcement learning (RL) agents. This paper demonstrates that learning state representations with supervision from Neural Radiance Fields (NeRFs) can improve the performance of RL compared to other learned representations or even low-dimensional, hand-engineered state i...
Preprint
Full-text available
Optimal sampling based motion planning and trajectory optimization are two competing frameworks to generate optimal motion plans. Both frameworks have complementary properties: Sampling based planners are typically slow to converge, but provide optimality guarantees. Trajectory optimizers, however, are typically fast to converge, but do not provide...
Preprint
We present a method to learn compositional predictive models from image observations based on implicit object encoders, Neural Radiance Fields (NeRFs), and graph neural networks. A central question in learning dynamic models from sensor observations is on which representations predictions should be performed. NeRFs have become a popular choice for...
Preprint
Robotic manipulation planning is the problem of finding a sequence of robot configurations that involves interactions with objects in the scene, e.g., grasp, placement, tool-use, etc. To achieve such interactions, traditional approaches require hand-designed features and object representations, and it still remains an open question how to describe...
Article
Full-text available
In this article, we propose deep visual reasoning, which is a convolutional recurrent neural network that predicts discrete action sequences from an initial scene image for sequential manipulation problems that arise, for example, in task and motion planning (TAMP). Typical TAMP problems are formalized by combining reasoning on a symbolic, discrete...
Preprint
Full-text available
Sequential decision-making and motion planning for robotic manipulation induce combinatorial complexity. For long-horizon tasks, especially when the environment comprises many objects that can be interacted with, planning efficiency becomes even more important. To plan such long-horizon tasks, we present the RHH-LGP algorithm for combined task and...
Preprint
This work proposes an optimization-based manipulation planning framework where the objectives are learned functionals of signed-distance fields that represent objects in the scene. Most manipulation planning approaches rely on analytical models and carefully chosen abstractions/state-spaces to be effective. A central question is how models can be o...
Article
Full-text available
Nonlinear programming is a complex methodology where a problem is mathematically expressed in terms of optimality while imposing constraints on feasibility. Such problems are formulated by humans and solved by optimization algorithms. We support domain experts in their challenging tasks of understanding and troubleshooting optimization runs of intr...
Chapter
We investigate active learning in Gaussian Process state-space models (GPSSM). Our problem is to actively steer the system through latent states by determining its inputs such that the underlying dynamics can be optimally learned by a GPSSM. In order that the most informative inputs are selected, we employ mutual information as our active learning...
Preprint
In the context of teleoperation, arbitration refers to deciding how to blend between human and autonomous robot commands. We present a reinforcement learning solution that learns an optimal arbitration strategy that allocates more control authority to the human when the robot comes across a decision point in the task. A decision point is where the...
Preprint
Full-text available
We investigate active learning in Gaussian Process state-space models (GPSSM). Our problem is to actively steer the system through latent states by determining its inputs such that the underlying dynamics can be optimally learned by a GPSSM. In order that the most informative inputs are selected, we employ mutual information as our active learning...
Preprint
Full-text available
In high-dimensional state spaces, the usefulness of Reinforcement Learning (RL) is limited by the problem of exploration. This issue has been addressed using potential-based reward shaping (PB-RS) previously. In the present work, we introduce Final-Volume-Preserving Reward Shaping (FV-RS). FV-RS relaxes the strict optimality guarantees of PB-RS to...
Preprint
Full-text available
In this extended abstract, we report on ongoing work towards an approximate multimodal optimization algorithm with asymptotic guarantees. Multimodal optimization is the problem of finding all local optimal solutions (modes) to a path optimization problem. This is important to compress path databases, as contingencies for replanning and as source of...
Conference Paper
Full-text available
In this paper, we introduce a Grasp Manifold Estimator (GraspME) to detect grasp affordances for objects directly in 2D camera images. To perform manipulation tasks autonomously it is crucial for robots to have such graspability models of the surrounding objects. Grasp manifolds have the advantage of providing continuously infinitely many grasps, w...
Conference Paper
Full-text available
This paper presents a teleoperation system that includes robot perception and intent prediction from hand gestures. The perception module identifies the objects present in the robot workspace and the intent prediction module which object the user likely wants to grasp. This architecture allows the approach to rely on traded control instead of direc...
Preprint
Full-text available
In this paper, we introduce a Grasp Manifold Estimator (GraspME) to detect grasp affordances for objects directly in 2D camera images. To perform manipulation tasks autonomously it is crucial for robots to have such graspability models of the surrounding objects. Grasp manifolds have the advantage of providing continuously infinitely many grasps, w...
Preprint
Full-text available
This paper presents a teleoperation system that includes robot perception and intent prediction from hand gestures. The perception module identifies the objects present in the robot workspace and the intent prediction module which object the user likely wants to grasp. This architecture allows the approach to rely on traded control instead of direc...
Preprint
Full-text available
Robotic assembly planning has the potential to profoundly change how buildings can be designed and created. It enables architects to explicitly account for the assembly process already during the design phase, and enables efficient building methods that profit from the robots' different capabilities. Previous work has addressed planning of robot as...
Conference Paper
Full-text available
In this paper, we tackle the problem of human-robot coordination in sequences of manipulation tasks. Our approach integrates hierarchical human motion prediction with Task and Motion Planning (TAMP). We first devise a hierarchical motion prediction approach by combining Inverse Reinforcement Learning and short-term motion prediction using a Recurre...
Conference Paper
Full-text available
In this paper, we tackle the problem of human-robot coordination in sequences of manipulation tasks. Our approach integrates hierarchical human motion prediction with Task and Motion Planning (TAMP). We first devise a hierarchical motion prediction approach by combining Inverse Reinforcement Learning and short-term motion prediction using a Recurre...
Conference Paper
Full-text available
Long-horizon manipulation tasks require joint reasoning over a sequence of discrete actions and their associated continuous control parameters. While Task and Motion Planning (TAMP) approaches are capable of generating motion plans that account for this joint reasoning, they usually assume full knowledge about the environment (e.g. in terms of shap...
Article
Sampling-based planning methods often become inefficient due to narrow passages. Narrow passages induce a higher runtime, because the chance to sample them becomes vanishingly small. In recent work, we showed that narrow passages can be approached by relaxing the problem using admissible lower dimensional projections of the state space. Those relax...
Preprint
Full-text available
Robotic manipulation of unknown objects is an important field of research. Practical applications occur in many real-world settings where robots need to interact with an unknown environment. We tackle the problem of reactive grasping by proposing a method for unknown object tracking, grasp point sampling and dynamic trajectory planning. Our object...
Conference Paper
Full-text available
As robots become more present in open human environments, it will become crucial for robotic systems to understand and predict human motion. In this paper, we present a novel dataset of full-body motion for everyday manipulation tasks. We additionally captured eye-gaze using a wearable pupil-tracking device. The dataset includes 180 min of motion c...
Chapter
Full-text available
Multi-robot motion planning problems often have many local minima. It is essential to visualize those local minima such that we can better understand, debug and interact with multi-robot systems. Towards this goal, we present the multi-robot motion explorer, an algorithm which extends previous results on multilevel Morse theory by introducing a com...
Preprint
Nonlinear programming targets nonlinear optimization with constraints, which is a generic yet complex methodology involving humans for problem modeling and algorithms for problem solving. We address the particularly hard challenge of supporting domain experts in handling, understanding, and trouble-shooting high-dimensional optimization with a larg...
Preprint
Full-text available
As robots become more present in open human environments, it will become crucial for robotic systems to understand and predict human motion. Such capabilities depend heavily on the quality and availability of motion capture data. However, existing datasets of full-body motion rarely include 1) long sequences of manipulation tasks, 2) the 3D model o...
Preprint
Full-text available
Efficient sampling from constraint manifolds, and thereby generating a diverse set of solutions of feasibility problems, is a fundamental challenge. We consider the case where a problem is factored, that is, the underlying nonlinear mathematical program is decomposed into differentiable equality and inequality constraints, each of which depends onl...
Preprint
Full-text available
Contact-based motion planning for manipulation, object exploration or balancing often requires finding sequences of fixed and sliding contacts and planning the transition from one contact in the environment to another. However, most existing algorithms do not take sliding contacts into account or consider them only for specialized scenarios. We pro...
Preprint
Full-text available
Sparse roadmaps are important to compactly represent state spaces, to determine problems to be infeasible and to terminate in finite time. However, sparse roadmaps do not scale well to high-dimensional planning problems. In prior work, we showed improved planning performance on high-dimensional planning problems by using multilevel abstractions to...
Preprint
Full-text available
Sampling-based planning methods often become inefficient due to narrow passages. Narrow passages induce a higher runtime, because the chance to sample them becomes vanishingly small. In recent work, we showed that narrow passages can be approached by relaxing the problem using admissible lower-dimensional projections of the state space. Those relax...
Preprint
Full-text available
We propose a formalism for shared control, which is the problem of defining a policy that blends user control and autonomous control. The challenge posed by the shared autonomy system is to maintain user control authority while allowing the robot to support the user. This can be done by enforcing constraints or acting optimally when the intent is c...
Article
Physical reasoning is a core aspect of intelligence in animals and humans. A central question is what model should be used as a basis for reasoning. Existing work considered models ranging from intuitive physics and physical simulators to contact dynamics models used in robotic manipulation and locomotion. In this work we propose descriptions of ph...
Preprint
Full-text available
Motion prediction in unstructured environments is a difficult problem and is essential for safe and efficient human-robot space sharing and collaboration. In this work, we focus on manipulation movements in environments such as homes, workplaces or restaurants, where the overall task and environment can be leveraged to produce accurate motion predi...
Preprint
Full-text available
Motion planning problems involving high-dimensional state spaces can often be solved significantly faster by using multilevel abstractions. While there are various ways to formally capture multilevel abstractions, we formulate them in terms of fiber bundles, which allows us to concisely describe and derive novel algorithms in terms of bundle restri...
Preprint
In state of the art model-free off-policy deep reinforcement learning, a replay memory is used to store past experience and derive all network updates. Even if both state and action spaces are continuous, the replay memory only holds a finite number of transitions. We represent these transitions in a data graph and link its structure to soft diverg...
Preprint
Full-text available
Algorithmic solutions for the motion planning problem have been investigated for five decades. Since the development of A* in 1969 many approaches have been investigated, traditionally classified as either grid decomposition, potential fields or sampling-based. In this work, we focus on using numerical optimization, which is understudied for solvin...
Conference Paper
Full-text available
In this paper, we propose a deep convolutional recurrent neural network that predicts action sequences for task and motion planning (TAMP) from an initial scene image. Typical TAMP problems are formalized by combining reasoning on a symbolic, discrete level (e.g. first-order logic) with continuous motion planning such as nonlinear trajectory optimi...
Preprint
In this paper, we propose a deep convolutional recurrent neural network that predicts action sequences for task and motion planning (TAMP) from an initial scene image. Typical TAMP problems are formalized by combining reasoning on a symbolic, discrete level (e.g. first-order logic) with continuous motion planning such as nonlinear trajectory optimi...
Article
Full-text available
Human arm movements are highly stereotypical under a large variety of experimental conditions. This is striking due to the high redundancy of the human musculoskeletal system, which in principle allows many possible trajectories toward a goal. Many researchers hypothesize that through evolution, learning, and adaption, the human system has develope...
Conference Paper
Full-text available
In this paper, we propose a deep neural network that predicts the feasibility of a mixed-integer program from visual input for robot manipulation planning. Integrating learning into task and motion planning is challenging, since it is unclear how the scene and goals can be encoded as input to the learning algorithm in a way that enables to generali...
Article
Full-text available
Motion planning problems often have many local minima. Those minima are important to visualize to let a user guide, prevent or predict motions. Towards this goal, we develop the motion planning explorer, an algorithm to let users interactively explore a tree of local-minima. Following ideas from Morse theory, we define local minima as paths invaria...
Conference Paper
Full-text available
We present a novel approach called Optimized Directed Roadmap Graph (ODRM). It is a method to build a directed roadmap graph that allows for collision avoidance in multi-robot navigation. This is a highly relevant problem, for example for industrial autonomous guided vehicles. The core idea of ODRM is, that a directed roadmap can encode inherent pr...
Preprint
We present a novel approach called Optimized Directed Roadmap Graph (ODRM). It is a method to build a directed roadmap graph that allows for collision avoidance in multi-robot navigation. This is a highly relevant problem, for example for industrial autonomous guided vehicles. The core idea of ODRM is, that a directed roadmap can encode inherent pr...
Preprint
Integrating robotic systems in architectural and construction processes is of core interest to increase the efficiency of the building industry. Automated planning for such systems enables design analysis tools and facilitates faster design iteration cycles for designers and engineers. However, generic task-and-motion planning (TAMP) for long-horiz...
Preprint
Logic-Geometric Programming (LGP) is a powerful motion and manipulation planning framework, which represents hierarchical structure using logic rules that describe discrete aspects of problems, e.g., touch, grasp, hit, or push, and solves the resulting smooth trajectory optimization. The expressive power of logic allows LGP for handling complex, la...
Conference Paper
Full-text available
Human movement prediction is difficult as humans naturally exhibit complex behaviors that can change drastically from one environment to the next. In order to alleviate this issue, we propose a prediction framework that de-couples short-term prediction, linked to internal body dynamics, and long-term prediction, linked to the environment and task c...
Preprint
Physical reasoning is a core aspect of intelligence in animals and humans. A central question is what model should be used as a basis for reasoning. Existing work considered models ranging from intuitive physics and physical simulators to contact dynamics models used in robotic manipulation and locomotion. In this work we propose path descriptions...
Preprint
Full-text available
Multi-robot motion planning problems often have many local minima. It is essential to visualize those local minima such that we can better understand, debug and interact with multi-robot systems. Towards this goal, we use previous results combining Morse theory and fiber bundles to organize local minima into a local minima tree. We extend this loca...
Conference Paper
Full-text available
In this work, we propose a framework to learn an inverse model of redundant systems. We address three problems. By formalizing what it actually means to learn an inverse model, we derive a method where the inverse model, represented as a neural network, is learned by minimizing an upper bound on the real performance error, which is provided by a fo...