1. Ph.D. Candidate Christoforos Mavrogiannis was selected to participate in the first Pioneers Workshop in the Robotics: Science and Systems conference (RSS) in June. Pioneers is a day-long invitation-only workshop for senior graduate students and postdocs, held in conjunction with the RSS conference, that seeks to bring together a cohort of the world’s top early career researchers in all areas of robotics. More details about the workshop can be found here.

  2. The paper “Following High-level Navigation Instructions on a Simulated Quadcopter with Imitation Learning”, by Valts Blukis, Ross Knepper, and Yoav Artzi, has been accepted to RSS 2018.


    We introduce a model and algorithm for following high-level navigation instructions by mapping directly from images, instructions and pose estimates to continuous low-level velocity commands for real-time control. The Grounded Semantic Mapping Network (GSMN) is a fully-differentiable neural network architecture that includes modular and interpretable perception, grounding, mapping and planning modules. It builds an explicit semantic map in the world reference frame. The information stored in the map is learned from experience, while the local-to-world transformation used for grid cell lookup is computed explicitly within the network. We train the model using a modified variant of DAGGER optimized for speed and memory. We test GSMN in rich virtual environments on a realistic quadcopter simulator powered by Microsoft AirSim and show that our model outperforms strong neural baselines and almost reaches the performance of its teacher expert policy. Its success is attributed to the spatial transformation and mapping modules which also provide highly interpretable maps that reveal the reasoning of the model.

  3. The article “Multi-Agent Path Topology in Support of Socially Competent Navigation Planning”, by Christoforos Mavrogiannis and Ross Knepper, has been accepted with minor revisions to the WAFR ‘16 special issue of the International Journal of Robotics Research (IJRR).

  4. The paper “Social Momentum: A Framework for Legible Navigation in Dynamic Multi-Agent Environments”, by Christoforos Mavrogiannis, Wil Thomason, and Ross Knepper, has been accepted to HRI 2018.

    From the paper:

    Intent-expressive robot motion has been shown to result in increased efficiency and reduced planning efforts for human or robot partners in implicitly or explicitly collaborative scenarios. Existing frameworks for generating intent-expressive robot behaviors have typically focused on applications in static or structured environments. Under such settings, emphasis is placed towards communicating the robot’s intended final configuration to other agents. However, in dynamic, unstructured and multi-agent domains, such as pedestrian environments, knowledge of the robot’s final configuration is not sufficiently informative, as it completely ignores the complex dynamics of interaction among agents. To address this problem, we focus on the generation of motion that communicates an agent’s intention toward a socially compliant collision avoidance strategy rather than its destination. We contribute a planning framework that estimates the intended avoidance strategies of others, superimposes them, and generates an expressive, socially compliant robot action that reinforces the expectations of others regarding the scene evolution. This action facilitates inference and decision making for everyone, as illustrated in the simplified topological pattern of agents’ trajectories at the end of the execution. Extensive simulations demonstrate that our framework consistently achieves significantly lower topological complexity, compared against common benchmark approaches in the area of multi-agent collision avoidance. The significance of this result for real world applications is demonstrated by a user study that revealed statistical evidence suggesting that multi-agent trajectories of lower topological complexity tend to enable observers to infer the intentions of actors more quickly and more accurately.

  5. The paper “Socially Competent Navigation Planning by Deep Learning of Multi-Agent Path Topologies”, by Christoforos Mavrogiannis, Valts Blukis, and Ross Knepper has been accepted to IROS 2017.

    From the paper:

    We present a novel, data-driven framework for planning socially competent robot behaviors in crowded environments. The core of our approach is a topological model of collective navigation behaviors, based on braid groups. This model constitutes the basis for the design of a human-inspired probabilistic inference mechanism that predicts the topology of multiple agents’ future trajectories, given observations of the context. We derive an approximation of this mechanism by employing a neural network learning architecture on synthetic data of collective navigation behaviors. Our planner makes use of this mechanism as a tool for interpreting the context and understanding what future behaviors are in compliance with it. The planning agent makes use of this understanding to determine a personal action that contributes to the context in the most clear way possible, while ensuring progress to its destination. Our simulations provide evidence that our planning framework results in socially competent navigation behaviors not only for the planning agent, but also for interacting naive agents. Performance benefits include (1) early conflict resolutions and (2) faster uncertainty decrease for the other agents in the scene.

  6. Second-year Ph.D. student Wil Thomason was awarded a four-year fellowship through the National Defense Science and Engineering Graduate Fellowship. He also received a three-year fellowship through the National Science Foundation’s Graduate Research Fellowship Program.

  7. The paper “Implicit Communication in a Joint Action”, by Ross Knepper, Christoforos Mavrogiannis, Julia Proft, and Claire Liang, has been nominated for a Best Paper Award at HRI 2017.

    For more on the paper, please see the announcement of its acceptance.

  8. The paper “Implicit Communication in a Joint Action”, by Ross Knepper, Christoforos Mavrogiannis, Julia Proft, and Claire Liang, has been accepted to HRI 2017.

    From the paper:

    Actions performed in the context of a joint activity comprise two aspects: functional and communicative. The functional component achieves the goal of the action, whereas its communicative component, when present, expresses some information to the actor’s partners in the joint activity. The interpretation of such communication requires leveraging information that is public to all participants, known as common ground. Much of human communication is performed through this implicit mechanism, and humans cannot help but infer some meaning — whether or not it was intended by the actor — from most actions. Robots must be cognizant of how their actions will be interpreted in context. We present a framework for robots to utilize this communicative channel on top of normal functional actions to work more effectively with human partners. We consider the role of the actor and the observer, both individually and jointly, in implicit communication, as well as the effects of timing. We also show how the framework maps onto various modes of action, including natural language and motion. We consider these modes of action in various human-robot interaction domains, including social navigation and collaborative assembly.

  9. The paper “Decentralized Multi-Agent Navigation Planning with Braids”, by Christoforos Mavrogiannis and Ross Knepper, was presented at WAFR 2016.

    From the paper:

    We present a novel planning framework for navigation in dynamic, multi-agent environments with no explicit communication among agents, such as pedestrian scenes. Inspired by the collaborative nature of human navigation, our approach treats the problem as a coordination game, in which players coordinate to avoid each other as they move towards their destinations. We explicitly encode the concept of coordination into the agents’ decision making process through a novel inference mechanism about future joint strategies of avoidance. We represent joint strategies as equivalence classes of topological trajectory patterns using the formalism of braids. This topological representation naturally generalizes to any number of agents and provides the advantage of adaptability to different environments, in contrast to the majority of existing approaches. At every round, the agents simultaneously decide on their next action that contributes collision-free progress towards their destination but also towards a global joint strategy that appears to be in compliance with all agents’ preferences, as inferred from their past behaviors. This policy leads to a smooth and rapid uncertainty decrease regarding the emerging joint strategy that is promising for real world scenarios. Simulation results highlight the importance of reasoning about joint strategies and demonstrate the efficacy of our approach.