Alejandro (Alex) Bordallo PhD

Alejandro (Alex) Bordallo


Research Interests

Many modern robotic applications require robots to function autonomously in dynamic environments including other decision making agents, such as people or other robots. This calls for fast and scalable interactive motion planning that is intention-aware.

We focus on real-time distributed navigation, constructing interactive motion models of other agents for counterfactual reasoning over their possible intentions. We develop a light-weight iterative planner for fluid pedestrian avoidance, utilising goal inference for long-range movement prediction. We implement on-line learning of a parameterised behaviour model as a computationally efficient alternative to offline training. This produces a scalable framework for navigation and intention prediction in dense multi-agent setups.

Our approach provides scientific insight into characteristics of human motion, such as agent awareness or share-of-effort in navigation. Our ultimate goal is performing interaction shaping in natural environments through robots, with connections to causal structure learning and language.

Publications:
2017
  Predicting future agent motions for dynamic environments
Previtali, F, Bordallo, AA, Iocchi, L & Ramamoorthy, S 2017, Predicting future agent motions for dynamic environments. in 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA). IEEE, pp. 94-99. DOI: 10.1109/ICMLA.2016.0024
Understanding activities of people in a monitored environment is a topic of active research, motivated by applications requiring context-awareness. Inferring future agent motion is useful not only for improving tracking accuracy, but also for planning in an interactive motion task. Despite rapid advances in the area of activity forecasting, many state-of-the-art methods are still cumbersome for use in realistic robots. This is due to the requirement of having good semantic scene and map labelling, as well as assumptions made regarding possible goals and types of motion. Many emerging applications require robots with modest sensory and computational ability to robustly perform such activity forecasting in high density and dynamic environments. We address this by combining a novel multi-camera tracking method, efficient multi-resolution representations of state and a standard Inverse Reinforcement Learning (IRL) technique, to demonstrate performance that is better than the state-of-the-art in the literature. In this framework, the IRL method uses agent trajectories from a distributed tracker and estimates a reward function within a Markov Decision Process (MDP) model. This reward function can then be used to estimate the agent’s motion in future novel task instances. We present empirical experiments
using data gathered in our own lab and external corpora (VIRAT), based on which we find that our algorithm is not only efficiently implementable on a resource constrained platform but is also competitive in terms of accuracy with state-of-the-art alternatives (e.g., up to 20% better than the results reported in [1]).
General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: Previtali, Fabio, Bordallo, Alejandro (Alex), Iocchi, Luca & Ramamoorthy, Subramanian.
Number of pages: 6
Pages: 94-99
Publication Date: 2 Feb 2017
Publication Information
Category: Conference contribution
Original Language: English
DOIs: 10.1109/ICMLA.2016.0024
2016
  Inverse eye tracking for intention inference and symbol grounding in human-robot collaboration
Penkov, S, Bordallo, AA & Ramamoorthy, S 2016, Inverse eye tracking for intention inference and symbol grounding in human-robot collaboration. in Robotics: Science and Systems Workshop on Planning for Human-Robot Interaction, 2016..
General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: Penkov, Svetlin, Bordallo, Alejandro (Alex) & Ramamoorthy, Subramanian.
Number of pages: 3
Publication Date: 18 Jun 2016
Publication Information
Category: Conference contribution
Original Language: English
  Automatic configuration of ROS applications for near-optimal performance
Cano Reyes, J, Bordallo, AA, Nagarajan, V, Ramamoorthy, S & Vijayakumar, S 2016, Automatic configuration of ROS applications for near-optimal performance. in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2016. IEEE, pp. 2177-2183. DOI: 10.1109/IROS.2016.7759347
The performance of a ROS application is a function of the individual performance of its constituent nodes. Since ROS nodes are typically configurable (parameterised), the specific parameter values adopted will determine the level of performance generated. In addition, ROS applications may be distributed across multiple computation devices, thus providing different options for node allocation. We address two configuration problems that the typical ROS user is confronted with: i) determining parameter values and node allocations for maximising performance; ii) Determining node allocations for minimising hardware resources that can guarantee the desired performance. We formalise thesee problems with a mathematical model, a constrained form of a multiple-choice multiple knapsack problem. We propose a greedy algorithm for optimising each problem, using linear regression for predicting the performance of an individual ROS node over a continuous set of parameter combinations. We evaluate the algorithms through simulation and we validate them in a real ROS scenario, showing that the expected performance levels only deviate from the real measurements by an average of 2.5%.
General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: Cano Reyes, Jose, Bordallo, Alejandro (Alex), Nagarajan, Vijayanand, Ramamoorthy, Subramanian & Vijayakumar, Sethu.
Number of pages: 7
Pages: 2177-2183
Publication Date: 1 Dec 2016
Publication Information
Category: Conference contribution
Original Language: English
DOIs: 10.1109/IROS.2016.7759347
  Task Variant Allocation in Distributed Robotics
Cano Reyes, J, White, D, Bordallo, AA, McCreesh, C, Prosser, P, Singer, J & Nagarajan, V 2016, Task Variant Allocation in Distributed Robotics. in Proceedings of Robotics: Science and Systems XII 2016. DOI: 10.15607/RSS.2016.XII.045
We consider the problem of assigning software processes(or tasks) to hardware processors in distributed robotics environments. We introduce the notion of a task variant, which supports the adaptation of software to specific hardware configurations.Task variants facilitate the trade-off of functional quality versus the requisite capacity and type of target execution processors.We formalise the problem of assigning task variants to processors as a mathematical model that incorporates typical constraints found in robotics applications; the model is a constrained form of a multi-objective, multi-dimensional, multiple-choice knapsack problem. We propose and evaluate three different solution methods to the problem: constraint programming, a constructive greedy heuristic and a local search metaheuristic. Furthermore, we demonstrate the use of task variants in a real instance of a distributed interactive multi-agent navigation system,showing that our best solution method (constraint programming)improves the system’s quality of service, as compared to the local search metaheuristic, the greedy heuristic and a randomised solution, by an average of 16%, 41% and 56% respectively.
General Information
Organisations: Neuroinformatics DTC.
Authors: Cano Reyes, Jose, White, David, Bordallo, Alejandro (Alex), McCreesh, Ciaran, Prosser, Patrick , Singer, Jeremy & Nagarajan, Vijayanand.
Number of pages: 9
Publication Date: Jun 2016
Publication Information
Category: Conference contribution
Original Language: English
DOIs: 10.15607/RSS.2016.XII.045
2015
  IRL-based prediction of goals for dynamic environments
Previtali, F, Bordallo, AA & Ramamoorthy, S 2015, IRL-based prediction of goals for dynamic environments. in IEEE International Conference on Robotics and Automation (ICRA) 2015, Workshop on Machine Learning for Social Robotics.
Understanding activities of people in a monitored environment is a topic of active research, motivated by applications requiring context-awareness. Inferring future agent motion is useful not only for improving tracking accuracy, but also for planning in an interactive motion task. Despite rapid advances in the area of activity forecasting, many state-of-the-art methods are still cumbersome for use on realistic robots. This is due to the requirement of having good semantic scene and map labelling, as well as assumptions made regarding possible goals and types of motion. Many emerging applications require robots with modest sensory and computational ability to robustly perform such activity forecasting in high density and dynamic environments. We address this by combining a novel multi-camera tracking method, efficient multi-resolution representations of state and a standard Inverse Reinforcement Learning (IRL) technique, to demonstrate performance that is sometimes better than the state-of-the-art in the literature. In this framework, the IRL method uses agent trajectories from a distributed tracker, and the output reward functions, describing the agent’s goal-oriented navigation within a Markov Decision Process (MDP) model, can be used to estimate the agent’s set of possible future activities. We conclude with a quantitative evaluation comparing the proposed method against others from the literature.
General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: Previtali, Fabio, Bordallo, Alejandro (Alex) & Ramamoorthy, Subramanian.
Number of pages: 6
Publication Date: 2015
Publication Information
Category: Conference contribution
Original Language: English
  Counterfactual Reasoning about Intent for Interactive Navigation in Dynamic Environments
Bordallo, A, Previtali, F, Nardelli, N & Ramamoorthy, S 2015, Counterfactual Reasoning about Intent for Interactive Navigation in Dynamic Environments. in Intelligent Robots and Systems (IROS), 2015 IEEE/RSJ International Conference on. IEEE, pp. 2943-2950. DOI: 10.1109/IROS.2015.7353783
Many modern robotics applications require robots to function autonomously in dynamic environments including other decision making agents, such as people or other robots. This calls for fast and scalable interactive motion planning that is intention-aware. We present a real-time motion planning framework that brings together a few key components including an interactive motion model for other agents and counterfactual reasoning over possible movement intentions of other agents. This yields a light-weight iterative planner that enables fluid motion when avoiding pedestrians, in parallel with goal inference for longer range movement prediction. This motion planning framework is coupled with a novel distributed visual tracking method that provides reliable and robust models for the current belief-state of the monitored environment. This combined approach represents a computationally efficient alternative to previously studied policy learning methods that often require significant offline training or calibration and do not yet scale to densely populated environments. We validate this framework with experiments involving multi-robot and human-robot navigation. Also, we further validate the tracker component on unconstrained pedestrian data sets.
General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: Bordallo, Alejandro, Previtali, Fabio, Nardelli, Nantas & Ramamoorthy, Subramanian.
Number of pages: 8
Pages: 2943-2950
Publication Date: 2015
Publication Information
Category: Conference contribution
Original Language: English
DOIs: 10.1109/IROS.2015.7353783

Projects:
A predictive causal model for improving decision making by learning through intervention tactics (PhD)