Published papers.

This work treats pick-and-place manipulation as start-to-goal-region motion planning, where valid grasps and placements define multiple workspace goals. It introduces a transformer-guided sampling-based tree planner that uses start and goal configurations plus visual observations to improve planning in constrained shelf environments. Simulated and real-world Franka Emika tests show faster planning, higher success rates, and effective transfer from simulation to robot execution.

Presents a social robot navigation framework for socially acceptable, kinodynamically feasible motion in dynamic indoor spaces. The approach combines world representation, multilayered path planning, and path-following control. A CNN-driven informed sampling strategy improves planner performance for online navigation. Benchmarks against state-of-the-art methods and real-world Reachy robot tests demonstrate the framework’s feasibility.

Presents an AR-supported supervisory control system for in-space assembly under communication delays. Operators define goals in a 3D AR interface, while behaviour trees handle execution and recovery. In a user study, the approach reduced completion time, effort, and workload compared with shared control under 0s and 2s latency.

A qualitative study of social robot navigation in real-world service settings across Ecuador and the UK, examining how robot behaviour, appearance, spatial constraints, and local context affect acceptance and user experience.

Presents an online social robot navigation framework for large, crowded indoor environments, combining social heatmap world modelling, multilayered sampling-based planning, and path-following control, with benchmarks and Pepper robot trials.

Introduces an online social robot navigation framework that generates collision-free and socially acceptable paths in uncontrolled crowded spaces using a modified sampling-based planner and social relevance validity checking.