Decoding (un)known opponent's game play, a real-life badminton eye tracking study Aditi Mavalankar, Snigdha Dagar, Kavita Vemuri* International Institute of Information Technology, Hyderabad, India. Email: aditi.mavalankar@students.iiit.ac.in , snigdha.dagar@research .iiit.ac.in, kvemuri@iiit.ac.in Abstract Is the underlying cognitive processes different when playing with an opponent whose game play is familiar to that of an unknown? This study filtered the advance cues extracted by expert and amateur players when paired with an opponent whose game play is familiar to that of an unknown opponent. Our data collected in a real-life naturalistic game play conditions suggests that at the beginning of the game and for the first serve only the opponent's torso is crucial for cues and as the game progresses the information from the feet seems to be sufficient for the expert players in contrast to the data from the amateur player. Subsequently the preparatory or quiet-eye period for the serves at the beginning of the game play was higher than for later serves for all player sets. The preparation time for known opponents by expert players was higher for the first serve than for the unknown opponents but by the fifth serve the duration was negligible. Analysis of complete rallies show that post-serve attention allocation to opponent's racket and shuttle-in-flight is paramount in the play for both sets of opponents. Taken together the results of this investigation suggests that expert player's visual attention was distinguishable to that of an amateur player and expert players quickly decode unknown opponent's competence fairly early in the game play and follow consistent pattern of visual search. The results from the preliminary experimental data suggest the possibility of understanding how humans employ dynamic pattern recognition models in visual-search. Introduction Data collected from real-life naturalistic conditions provides insight into anticipation, prediction and rapid re- adjustments processes applied by players in a sport like badminton. Analysis of data like eye gaze collected from players engaged in real-time naturalistic game play can provide an accurate reflection of player behavior. Inferences on the underlying cognitive and motor skills can be derived to a certain extent from two main indices, visual search patterns and fixation duration in the preparatory, anticipatory and execution phases of the game play. In this study we report scanpath analysis reflecting the visual search in later two phases with emphasis on the quiet eye period in the preparatory phase. We do this by comparing data from three players paired against opponents with whom they have played before and others whose game play was unknown. A wearable eye tracker (Tobii Glasses I) was used to collect saccadic eye movement and the fixation duration, which is an estimate of attention allocation at particular regions of interest important for game strategy, though it was shown that other factors like stress can also influence fixations (Abernethy, 1988, 1990). The quiet-eye period in our case is the preparatory phase of the player just before executing the serve. This period is defined as the time taken to access task relevant cues and strategize appropriate motor actions (Vickers, 1996). Previous studies on badminton which looked at differences in experts versus novice game play using spatial occlusion concept (Abernethy & Russel, 1987a,b) show the former exhibited better anticipatory behavior while the later needed more information for decision making. In the same study a video recording of game play was shown to novice and expert players who wore a mobile eye tracker and the fixation duration at five distinct regions – shuttle-in-flight, opponent's arm,racket,head,face,legs – revealed that both groups have similar early fixations regions though time on the racket and arm was more for the expert while it was the head area for the novice. Secondly they report that the order of the fixation on the cues was not dissimilar. A similar study on tennis (Goulet et al., 1989) aimed to understand visual search pattern reported that focus was on shoulder/trunk of the opponent in the preparation stage and then shifts to the racket during the execution phase while novices depend on more cues by using pre-recorded game play as stimulus. Singer et al., (1996) also used simulated tennis play and found differences between skilled and non- skilled player in visual-search , reaction time and decision accuracy with non-skilled players fixating longer on the opponent's head and less systematic in the tracking of the in- flight ball. It was also shown that player's ability to anticipate opponent's intentions from postural cues is an advantage (Rowe & McKenna, 2001) and a skill that is acquired over time by players. Using a more sensitive eye tracker, Abernethy (1990) conducted experiment with video recorded squash game play projected on a huge screen on the wall of the squash court. The players were positioned in the court and the data showed that experts fixate on head/arm more than on the racket as compared to novice players, from which they inferred that experts are capable of eliciting advance cues just from posture. The fixation times were not different for the two groups and visual search pattern variation was not evident. A meta-analysis of three decades of work (Mann et al. 2007) which compared the attentional allocation of experts and novices report that the former have fewer long duration fixations translating to possible higher information extraction ( Williams et al., 1999) quicker. The quiet-eye time , as another gaze behavior index, of experts was found to be higher when compared to less-skilled players across 211