Danesh Tarapore
Danesh Tarapore is an Associate Professor of Robotics in the School of Electronics and Computer Science at the University of Southampton. His research focuses on resilient autonomy: how robots can adapt, recover and cooperate when operating in complex real-world environments where conventional assumptions about sensing, mobility and control break down.
His work spans adaptive and embodied robotics, swarm and multi-robot systems, and field robotics. He has contributed to research on robot adaptation following damage, including work published in Nature and featured on its cover, and subsequently developed a broader research programme around resilience and adaptation in autonomous systems.
A major current focus is the use of forests as accessible, demanding real-world testbeds for robotics. His group works with wheeled and legged robots on problems including navigation under degraded perception, physical entrapment and recovery, low-cost forest sensing, and scalable environmental monitoring using multiple robots.
Earlier research has included resilient robot swarms and environmentally adaptive marine robotic systems. He is particularly interested in multidisciplinary academic and industry collaborations that bring robotics to difficult real-world problems.
Danesh received his PhD from the University of Lausanne and his MEng from IIT Bombay. He was previously a Marie Skłodowska-Curie Fellow and has led research funded by EPSRC and the Alan Turing Institute.
Projects
- Scalable robotic monitoring of forest environments
- Resource-Efficient Collective Decision Making in Robot Swarms
- Incremental learning on resource-constrained embedded systems
- User-aware adaptive human-robot interaction
- Resilient forest autonomy
- Towards Flexible Autonomy for Swarms in Dynamic and Uncertain Environments
- Marine Robotic Swarm Operations
- Rapid fault-recovery strategies for resilient robot swarms
Publications
- ForEnt: a multi-modal dataset for characterizing quadruped robot entrapments in forest environments
- Investigating the role of implicit signals in adaptive user-aware human-robot interactions
- Blind-Wayfarer: A minimalist, probing-driven framework for resilient navigation in perception-degraded environments
- HRI-SENSE: a multimodal dataset on social and emotional responses to robot behaviour
- RoboButler: frustration-aware assistive user localisation for social robots in office environments
- SubCDM: collective decision-making with a swarm subset
- User-aware collaborative learning in human-robot interactions
- Evolutionary data subset selection for class-Incremental learning on memory-constrained systems
- Trade-offs of dynamic control structure in human-swarm systems
- An embarrassingly simple approach for visual navigation of forest environments
- Efficient simulation of wave glider dynamics and validation with trans-Pacific voyages
- End-to-End learning for visual navigation of forest environments
- Methods for the deployment of a swarm of wave gliders to monitor tropical cyclones
- Collective decision making in communication-constrained environments
- From Intelligent Agents to Trustworthy Human-Centred Multiagent Systems
- Quality-Diversity Meta-Evolution: Customizing Behavior Spaces to a Meta-Objective
- Resilient robot teams: a review integrating decentralised control, change-detection, and learning
- Anytime and efficient multi-agent coordination for disaster response
- ASVLite: a high-performance simulator for autonomous surface vehicles
- Designing a user-centered interaction interface for human–swarm teaming
- Large-scale, dynamic and distributed coalition formation with spatial and temporal constraints
- On the use of feature-maps for improved quality-diversity meta-evolution
- Rapidly adapting robot swarms with Swarm Map-based Bayesian Optimisation
- Anytime and efficient coalition formation with spatial and temporal constraints
- Learning behaviour-performance maps with meta-evolution
- Low-viewpoint forest depth dataset for sparse rover swarms
- QED: using Quality-Environment-Diversity to evolve resilient robot swarms
- Sparse robot swarms: Moving swarms to real world applications
- The surprising creativity of digital evolution: a collection of anecdotes from the evolutionary computation and artificial life research communities
- Fault detection in a swarm of physical robots based on behavioral outlier detection
- Adaptive online fault diagnosis in autonomous robot swarms
- Fault diagnosis in robot swarms: an adaptive online behaviour characterisation approach
- Generic, scalable and decentralized fault detection for robot swarms
- Towards fault diagnosis in robot swarms: an online behaviour characterisation approach
- How do different encodings influence the performance of the MAP-Elites algorithm?
- Abnormality detection in robots exhibiting composite swarm behaviours
- Evolvability signatures of generative encodings: Beyond standard performance benchmarks
- Robots that can adapt like animals
- To err is robotic, to tolerate immunological: fault detection in multirobot systems
- Comparing the evolvability of generative encoding schemes
- Optimizing the crossregulation model for scalable abnormality detection
- Abnormality detection in multiagent systems inspired by the adaptive immune system
- Clonal expansion without self-replicating entities
- Environment classification in multiagent systems inspired by the adaptive immune system
- Limitations of response thresholds models of division of labor
- Neural networks as mechanisms to regulate division of labor
- Task-dependent influence of genetic architecture and mating frequency on division of labour in social insect societies
- Influence of the level of polyandry and genetic architecture on division of labour
- Information-theoretic approach to embodied category learning
- Quantifying patterns of agent--environment interaction
- Fingerprinting agent-environment interaction via information theory